
In Progress
Posted
Software Engineering Task Author (Contract) About the Role We're looking for an experienced software engineer to design and build Frontier-style software engineering tasks — long-horizon, repository-based coding challenges used to train and evaluate AI coding agents. You'll take real engineering problems from your own area of expertise and turn them into rigorous, verifiable tasks: a seeded repository, a clear public specification, and an automated grader that checks observable behavior (builds, hidden test suites, protocol conformance, concurrency/recovery scenarios, deterministic replay, numeric budgets, etc.). This is deep, research-grade work — closer to writing a hard systems/algorithms exam with an autograder than to typical QA or content work. What You'll Do Design non-trivial engineering problems grounded in real-world systems (e.g., concurrency bugs, recovery/consistency issues, legacy modernization, protocol implementation, performance-constrained rewrites). Build a starter repository, write a complete public specification ([login to view URL]), and implement a reference solution that solves the task correctly. Write automated grading code that measures exactly what the instructions ask for — no hidden requirements, no LLM judges, no shortcuts. Produce a no-op/naive baseline to confirm the task has real difficulty, and adversarial "attack" submissions to confirm the grader can't be gamed. Validate, iterate, and submit tasks via pull request through a structured review pipeline. Use AI tools to accelerate parts of your workflow (explaining code, debugging validation errors, reviewing your own logic) — but the engineering judgment and task design must be your own. What We're Looking For Strong professional software engineering background (backend systems, distributed systems, compilers, low-level/systems programming, or similar) — ideally in an area where you have real depth and war stories, not just familiarity. Comfort with concurrency, correctness, and testing — the ability to reason precisely about what a grader should and shouldn't check. Experience writing clear technical specifications and/or authoring hard technical interview problems, coding challenges, or test suites. Git/GitHub workflow fluency (branches, PRs, CI). Self-directed: comfortable working from written guidelines, validating your own work, and iterating based on automated feedback and review. Bonus: experience with reinforcement learning, model evaluation, or "reward hacking" adversarial thinking (i.e., trying to break your own grader before someone else does). Nice to Have A specific technical niche you know cold (e.g., database internals, network protocols, embedded systems, compilers/language runtimes, numerical computing) that would make for a compelling, hard-to-fake task. Prior experience creating technical assessments, benchmarks, or eval datasets. Engagement Details Contract / freelance, task-based. Deliverables are reviewed against defined structure, CI, and quality checks before acceptance. Ongoing support and clarification provided via a shared Discord community. To apply, please share examples of complex systems you've built or debugged, any prior experience authoring technical assessments or benchmarks, and a brief note on what kind of engineering problem you'd want to turn into a task.
Project ID: 40664309
41 proposals
Remote project
Active 1 min ago
Set your budget and timeframe
Get paid for your work
Outline your proposal
It's free to sign up and bid on jobs

Hi, Creating Frontier style engineering tasks requires more than writing difficult code. The task must be precise, testable, reproducible, and difficult to game. A strong workflow combines a realistic repository, clear specifications, reference implementation, automated grading, baseline testing, and adversarial validation to ensure the grader measures exactly what is required. That is where my expertise comes in. I specialize in software engineering, backend development, AI development, Git workflows, testing, and building reliable web and software systems. I can contribute strong engineering judgment and create rigorous tasks with practical real world scenarios and verifiable results. Warm regards, Aadil Shah
$5 USD in 40 days
0.0
0.0
41 freelancers are bidding on average $10 USD/hour for this job

With a passion for clean and functional solutions combined with my extensive skills in Backend Development, I believe I'm uniquely suited to the challenging task of creating detailed high-level engineering problems your team requires. I understand the importance of conducting research-grade work that aligns with AI coding agents' needs. This experience would be valuable when writing comprehensive public specifications and issuing precise instructions for coding challenges. I have an in-depth background in backend systems, distributed systems, and low-level/systems programming, areas where my proficiency is grounded on real-world tasks. Additionally, I have a profound understanding of concurrency, correctness, and testing — a skill that aligns perfectly with needs to reason exact expectations for grading codes without shortcuts or hidden requirements. To accelerate the workflow process, I also possess knowledge of Git/GitHub protocols and thus comfortable in working with branches pull requests and CI. My familiarity with AI tools further helps me provide results in shorter turnaround times without compromising efficiency and quality. With my comprehensive skillset and strong work ethic, let's collaborate to create Frontier-style tasks that set your company apart from the competition.
$5 USD in 40 days
5.1
5.1

Hi, I can create rigorous software engineering tasks with clear specifications, reference solutions, automated graders, and adversarial tests. I’m experienced with debugging, testing, Git/GitHub workflows, concurrency, and edge-case validation. I’d be happy to share relevant work samples and discuss a suitable task idea. Best Regards, Shakila Naz
$5 USD in 40 days
4.9
4.9

I’m an experienced software developer with 10+ years of experience building and debugging complex backend, API, automation, and systems software. I can turn real engineering problems into rigorous, reproducible evaluation tasks with a seeded repository, clear specification, reference implementation, deterministic automated grader, and adversarial tests. I’m comfortable with Git/GitHub, CI, debugging, concurrency, protocol behavior, edge cases, and designing tests that verify observable behavior rather than relying on subjective evaluation. For a task example, I’d propose a fault-tolerant concurrent job-processing system involving retries, ordering, idempotency, recovery, and deterministic replay—challenging enough to expose subtle implementation flaws while remaining objectively gradable. I can start with a pilot task and iterate based on your review pipeline.
$5 USD in 40 days
3.1
3.1

Hi There!!! You are looking for an experienced software engineer to design repository-based Frontier-style coding tasks, public specifications, baseline solutions, and automated autograders to evaluate AI coding agents. I HAVE ALREADY WORKED ON SIMILAR SOFTWARE ENGINEERING TASK AUTHORING AND BENCHMARKING PROJECTS BEFORE. Services provided for your project: * Designing non-trivial systems problems around concurrency, recovery, and protocol logic * Starter repository setup with detailed instruction files and baseline reference solutions * Automated autograder development measuring observable behavior and deterministic test coverage * Adversarial attack verification to ensure autograders cannot be gamed * Structured GitHub pull request submissions with clean test pipelines Please join me in chat so we can discuss task topics and repository specifications. Best Regards, Hussain Ahmed
$2 USD in 40 days
1.5
1.5

Hey! Let's get right to it. Creating rigorous, real-world coding challenges requires not just technical skill but also a clear understanding of key concepts like concurrency bugs and protocol implementation. I've built starter repositories and automated grading systems before, so I can ensure the tasks are both challenging and verifiable. Open to your feedback on scope and price. Appreciate it! - Dobrivoje.J
$6 USD in 40 days
1.0
1.0

Hi , You need an expert in Engineering, Java, Backend Development, Software Engineering, Git, AI Development, Software Testing and Verilog / VHDL, and I have a tailor-made solution ready for you. Your project brief instantly reminded me of a recent client who faced similar challenges, and I know exactly how to execute this flawlessly for your specific needs. To ensure we hit the ground running, I have three quick questions: Are there any additional technical details or constraints not mentioned in the brief? What is the primary hurdle currently blocking your progress on this? What is your strict timeline for completion? Why trust me with your project? The Record: 250+ Projects. 6+ Years. 100+ consecutive 5-star reviews. The Standard: Zero misses. I don’t just finish the job; I guarantee flawless execution. The Availability: Full-time freelancer, online 9 AM - 9 PM EST. My biggest "heavy-hitter" projects are kept off my public portfolio to protect client confidentiality. Click 'CHAT', and I’ll immediately send over relevant, private samples so you can see the standard of my work firsthand. Best regards, Muhammad Arsalan
$10 USD in 30 days
0.0
0.0

Hello, Having spent the past few years honing my proficiency in AI, full-stack and mobile app development, I believe I have the skills and expertise you are looking for in designing Frontier-style tasks. My approach to software engineering is deeply rooted in solving complex real-world problems with creativity and efficiency, which aligns perfectly with the task requirements you outlined. One major aspect of my technical acumen that sets me apart is my ability to build and scale groundbreaking applications, including AI-powered systems. This not only equips me with an understanding of the theory behind these tasks but also a pragmatic outlook towards their implementation. Additionally, my experience with code review and CI will ensure that your needs are met promptly while adhering to the highest quality checks. Furthermore, my familiarity with Git/GitHub workflows and my self-directed working style make me an ideal candidate for this role. I'm highly-comfortable in validating my own work, following instructions thoroughly and rapidly iterating based on automated feedback and review. I am confident that choosing me would deliver amazing outcomes for your projects as I would leverage AI tools to speed up my workflow without compromising on task design quality or creativity. Thanks!
$50 USD in 25 days
0.0
0.0

Hey , I just went through the project description, and I see you are looking for someone experienced in Software Engineering, Git, Backend Development, Software Testing, Engineering, AI Development, Java and Verilog / VHDL. It instantly reminded me of a client who faced similar challenges, and I knew I had a tailor-made solution for it. Please review my profile to confirm that I have great experience working with these tech stacks. While I have few questions: • Is there anything else you’d like to add to the project details? • What’s the top hurdle you’re facing with this project? • What is the timeline to get this done? Why Choose Me? 250+ Projects. 5 Years. Zero Misses. My reputation is built on a single metric: Flawless Execution. While others promise quality, my last 100+ consecutive 5-star reviews prove it. I don’t just finish the job; I set the standard. The portfolio here is just the tip of the iceberg. To respect client confidentiality, my recent heavy-hitters aren't public, but I can share them 1-on-1. Regards, Ali .
$10 USD in 30 days
0.0
0.0

Hello, As an experienced full stack developer with over 10 years of experience, I bring a unique set of skills that align perfectly with the demanding scope of this role. My applicable expertise includes backend development as well as solid understanding of database architecture and system optimization. These proficiencies have been honed in complex scenarios similar to those sought in this project description. One example of my specialized knowledge is in SaaS platforms and MVP development where I undertook tasks involving performance-constrained rewrites and protocol implementation, which closely mirrors the challenges envisioned in this role. Moreover, I can confidently navigate Git/Github workflow as demonstrated by my proficiency in branches and pull requests -- a quality essential for someone working remotely. My communication skills are proven through active engagement on platforms such as Discord, essential for continuous support throughout the project. Finally, my wealth of experience authoring complex code will ensure tasks are designed with both depth and authenticity, bringing the right level of difficulty ensuring maximum efficacy. At its core, this project appears to require robust engineering judgment from start-to-end -- exactly what characterizes my approach to work. Please take into account my adaptability, diligence in validating my own work supported by automated feedback, all reflected in my successful track re Thanks!
$20 USD in 30 days
0.0
0.0

⚡ Timeline : 1 day | Cost: $100 ⚡ Hi, You need an experienced software engineer to create rigorous Frontier-style coding tasks, including a seeded repository, clear technical specification, reference solution, automated grader, baseline and adversarial submissions, with strong validation around correctness, concurrency, recovery, and edge cases. I’m sure I can deliver a perfect result within 1 day as you wanna. I’d be happy to jump on a quick chat to discuss in more details or get started right away. Looking forward to hearing from you!
$5 USD in 40 days
0.0
0.0

Hi there, I’d love to help create Frontier-style engineering tasks. My background is in systems-focused software engineering, with experience designing, debugging, and validating behavior in complex codebases where correctness, reproducibility, and edge cases matter. I’m especially interested in turning real engineering problems into rigorous tasks with seeded repos, precise specs, reference implementations, and graders that measure observable behavior only. The kind of challenge I’d enjoy most is one involving concurrency, recovery, protocol correctness, or deterministic replay, where the task is hard to fake and the grader is truly robust. I’m comfortable working in structured review pipelines, iterating on specs and tests, and using AI tools as accelerators while keeping the engineering judgment human-led. Best, Panagiotis
$20 USD in 20 days
0.0
0.0

Having a well-rounded background in software engineering, I believe I'm the ideal fit for this project. With a specialisation in backend systems and distributed systems, I've encountered a variety of complex challenges that mirror what you're looking for in this role. My extensive understanding of Git and GitHub lends well to the task of creating repositories, managing branches, and submitting thorough pull requests. Additionally, my experience extends beyond basic problem-solving; I have also authored numerous hard technical interview problems and coding challenges. This skill requires me to think outside the box and find real-world issues to design into my tasks - similar to what you are seeking with your Frontier-style tasks. These experiences have honed my ability to write clear technical specifications, code instructively, and implement them correctly. My work ensures there are no hidden requirements, shortcuts, or ambiguous expectations; yielding quality outputs.
$6 USD in 3 days
0.0
0.0

Hi there, I am an AI Full Stack Developer with around four years of experience building complex backend systems, AI workflows, and automated testing solutions. I am comfortable turning real engineering problems into clear specs, seeded repositories, reference solutions, and reliable automated graders. I can create challenging tasks around concurrency, recovery, correctness, performance, or distributed systems, while testing naive and adversarial submissions to prevent reward hacking. I would be glad to discuss a strong task idea from my experience and contribute long term. Thanks, Srdan.
$5 USD in 40 days
0.0
0.0

★★★★★★★★★★★★★★★ I can work full time for you. ★★★★★★★★★★★★★★★ I understand you need rigorous repo-based tasks with deterministic graders. I can design concurrency, recovery, protocol, and backend correctness challenges. I use Git, CI, hidden tests, adversarial cases, and reproducible grading. Task idea: a crash-recoverable job queue with replay and idempotency bugs. Thank you for hiring me.
$5 USD in 40 days
0.0
0.0

Hi, Our company is the right choice for this project as our expertise is in software development and Artificial intelligence. Payment will be requested only upon task completion. The budget is totally negotiable. Portfolio will be shown as requested. Looking forward to collaborating.
$2 USD in 40 days
0.0
0.0

Hi, Your Frontier-style task creation role aligns well with my experience in software engineering, debugging complex systems, automated testing, Docker, CI/CD, and repository-based development. I’m particularly interested in designing tasks where the specification, starter repository, reference solution, and grader must all align precisely. I understand the importance of making requirements objectively testable, validating the reference solution, and using naive and adversarial submissions to ensure the grader cannot be easily gamed. I have worked on backend systems, APIs, databases, concurrency-related logic, CI/CD workflows, and complex debugging tasks where correctness and reproducibility are critical. I’m comfortable taking an existing engineering problem, turning it into a clear technical specification, building the required repository and tests, and iterating through automated and human review. One task I’d be interested in creating would involve transactional consistency and concurrency: a system that appears correct under normal requests but fails under concurrent operations or partial failures. The challenge would require understanding the existing architecture, identifying the underlying correctness issue, implementing a robust solution, and passing deterministic regression and adversarial tests. I’m interested in a long-term collaboration and comfortable working through GitHub PRs and structured review workflows. Best, Harrison
$10 USD in 40 days
0.0
0.0

Hi there, I am a Full Stack Developer ready to help you build a high-performing, scalable, and secure application. I bring a strategic approach to problem-solving, clean coding standards, and proactive communication to ensure project success. What I bring to your project: High-quality front-end & back-end execution Clean, well-documented, and maintainable code Regular progress updates and timely delivery I am available to start immediately. Let's connect to discuss your exact requirements! Best regards, Hamza Soltan
$4 USD in 35 days
0.0
0.0

Hi. I can help design Frontier-style software engineering tasks by combining systems engineering expertise with clear specifications, reference solutions, and automated graders. I would build reproducible repositories, define observable requirements, test concurrency and recovery scenarios, and validate solutions with baseline and adversarial submissions to ensure challenging evaluations. What technical areas or benchmark standards should these tasks prioritize for your evaluation pipeline? I have experience in software engineering, backend development, testing, and building reliable systems where correctness and performance are critical. I would like to discuss the project in more detail through a chat and explore how my experience can help create high-quality engineering evaluations.
$7 USD in 40 days
0.0
0.0

Hello, I'm Bharghav, bringing over 10 years of experience in matching job skills, particularly focused on Java and software testing. I understand your need for an experienced software engineer to develop rigorous, Frontier-style engineering tasks. My approach will involve designing non-trivial problems that reflect real-world challenges, crafting a detailed public specification, and implementing an automated grading system to assure the task's integrity. I will leverage my expertise to create a comprehensive and engaging evaluation environment suitable for AI coding agents. Let’s start a chat to discuss your vision in more detail. Best regards, bhargav922002
$5 USD in 3 days
0.1
0.1

Hi, This is exactly the kind of deep, precise work I'd enjoy. Designing a genuinely hard task with a grader that can't be gamed requires the same discipline as writing a rigorous exam question, get the spec loose or the grader shallow, and the task falls apart under scrutiny. Systems I've built or debugged: I debugged a race condition in a connection pool under high concurrency for a backend service handling thousands of simultaneous requests, tracing it to a subtle lock-ordering issue that only surfaced under load. I've also built a partial custom binary protocol implementation for a legacy system migration, including strict conformance testing against the original spec. Prior assessment/benchmark experience: I've written technical interview problems for hiring rounds, including test suites designed to catch edge cases candidates commonly miss, and I regularly write thorough automated test coverage as part of normal engineering work, which overlaps closely with grader design discipline. A problem I'd turn into a task: a recovery/consistency scenario in a simple key-value store, crash mid-write, then verify recovery to a consistent state without data loss. It's hard to fake, has clear observable correctness criteria, and resists shortcuts since partial implementations fail under adversarial crash timing. I'd approach grader design adversarially from the start, trying to break my own checks before submitting. Thanks,
$12 USD in 40 days
0.0
0.0

atlanta, United States
Payment method verified
Member since Oct 24, 2019
$2-8 USD / hour
$2-8 USD / hour
$2-8 USD / hour
$2-8 USD / hour
$2-8 USD / hour
$15-25 USD / hour
₹1500-12500 INR
₹750-1250 INR / hour
$8-15 CAD / hour
£20-250 GBP
₹12500-37500 INR
₹1800-2800 INR / hour
₹1500-12500 INR
$25-50 USD / hour
$15-25 USD / hour
₹750-1250 INR / hour
$1500-3000 USD
₹75000-150000 INR
$30-250 NZD
₹600-1500 INR
₹12500-37500 INR
$750-1500 USD
$500 USD
$8-15 USD / hour
$250-750 USD