AI Resume Parser & Evaluator

@Krrishniresh7788

Hey there, I see what you trying to do and i can help you build the exact system you need. My question is, are you open to using LLM's like chatgpt or deepseek for the project? with gen AI tools we can build a smart system, let me know what you think

@hoangvanp

Hello, Building an AI resume parser and evaluator involves more than just extracting data—it's about providing recruiters with a clear snapshot of candidate competency. I propose starting by utilizing Python and NLP libraries like spaCy for efficient processing. I would begin by reviewing the existing resume formats (PDF, DOCX, TXT) and structuring the output JSON with key sections like contact information, work experience, education details, extracted skills, skill-level score, and experience-relevance score. The emphasis would be on accuracy and consistency, ensuring recruiters can easily filter candidates based on these metrics. My previous experience in developing similar parsers has equipped me to tackle this project effectively. I look forward to discussing further details and commencing work promptly. Best regards,

@kaimenyijohn5

Resume Parser with AI Scoring – Python, NLP, REST API, JSON Output Hello, I'm John K. — MSc Economics & Statistician with 15+ years and 1,000+ projects (4.9⭐). I specialize in Python, NLP, and data extraction. You need a resume parser that extracts contact, work, education, and skills — plus Skill-Level and Experience-Relevance scores (numeric scale). Must accept PDF, DOCX, TXT and return JSON via REST/local function. How I'll approach it: Build file ingestion for PDF/DOCX/TXT Extract sections using spaCy NER and regex Mine skills using transformers or trained model Score Skill-Level (1-10) and Experience-Relevance (1-10) Package as REST API (FastAPI) or local function Deliver code, README, 5 sample resumes + JSON What you'll receive: ✅ Clean Python code ✅ JSON output (contact, work, education, skills, scores) ✅ README with setup and scoring logic ✅ 5 sample resumes + JSON (≥90% accuracy) Timeline: 7-10 days. I'm ready. Drop a message to confirm the scoring scale. Looking forward, John K.

@shayankhan333

The trickiest part of resume parsing isn't extraction, it's normalizing messy date formats and inconsistent job titles into a structure that's actually filterable. That's where I'll focus first. I'll build the pipeline in Python using spaCy for entity extraction and a lightweight transformer model for the scoring layer, returning structured JSON from PDF, DOCX, and TXT inputs via a clean REST endpoint. One thing worth flagging: for the skill-level scoring, a hybrid approach works better than pure NLP. Pairing keyword frequency with contextual signals like years-in-role and achievement language gives scores recruiters actually trust, versus just counting mentions. I can have a working build with the five validated sample outputs within 3 to 4 days. Best regards, Shayan

@sufyanaslamch

Hello Sir, I have carefully read your requirements and can build a reliable AI-powered resume parser in Python that accepts PDF, DOCX, and TXT files and returns clean structured JSON. The solution will extract and organise: • Contact information • Work experience, companies, roles, dates, and achievements • Education details • Technical and soft skills • Skill-level score • Experience-relevance score I recommend using a hybrid approach with spaCy, transformer models, regex rules, and configurable skill dictionaries. This is more accurate than relying on a single AI model and makes the parser easier to improve over time. The system can be delivered as a simple REST API and also as a local Python function. Scoring will follow a clear numeric scale based on skill depth, years of experience, recency, role relevance, achievements, and matching keywords. You will receive: • Clean and documented Python source code • Structured JSON output • REST API endpoints • Error handling for different resume layouts • README with setup and scoring explanation • Five sample resumes with generated JSON • Accuracy testing and adjustment against the agreed samples Estimated delivery time is 10 to 14 days, depending on the resume formats and scoring rules. I am waiting for your kind response. Thanks

@somendersingh96

Hello, I can build a high-accuracy AI-powered resume parser that extracts structured candidate information and generates intelligent candidate scoring for recruitment workflows. What I'll deliver: * Resume parsing for PDF, DOCX, and TXT formats * Extraction of contact details, work experience, education, achievements, and skills * AI-powered Skill Level and Experience Relevance scoring on a consistent numeric scale * Clean REST API (or local Python function) returning structured JSON * Well-documented Python code using spaCy, Transformers, and OCR (where required) * README with setup instructions, scoring methodology, and sample outputs * Five sample resumes with generated JSON achieving high extraction accuracy The solution will be modular and scalable, making it easy to integrate into your ATS or recruitment platform while supporting future enhancements such as candidate ranking and job matching. I have experience building AI-powered document processing, NLP pipelines, REST APIs, and an intelligent data extraction system, and I can deliver a clean, production-ready solution within the agreed timeline. Best regards, Somender Singh

@sanddep5

With over [X amount of years] in the realm of Data Extraction and Processing, I have not only developed a sharp knack for deciphering complex datasets like resumes, but also honed in my skills in Python that would make me a perfect fit for your AI Resume Parser & Evaluator project. Moreover, I have a vast experience working with Java and OpenAI, which will be quite handy while extracting data and assigning clear Skill-Level assessments and Experience-Relevance scores that you require. In regards to the resume-parser component of your project, I have always been passionate about Natural Language Processing (NLP), which has enabled me to leverage top-tier libraries - like spaCy, transformers, etc. - to create clean well-documented codes with pertinent data points extracted efficiently. Having a strong background in building Business Intelligence solutions, I also understand the importance of simplicity and reliability which led me to specialize in utilizing flexible yet powerful tech stacks such as FastAPI, PostgreSQL, MySQL, Pandas, NumPy and Plotly alike.