LLM AI Engineer for Agentic Workflow

# Job Description: LLM Data Scientist / AI Engineer – Agentic AI & RAG ## Role Overview We are hiring an LLM Data Scientist / AI Engineer to help build advanced AI products using Large Language Models, Retrieval-Augmented Generation, agentic AI workflows, and applied machine learning. This role is ideal for someone who can combine strong data science skills with hands-on engineering ability to design, evaluate, and deploy intelligent AI systems. The candidate will work on building AI agents, RAG pipelines, model evaluation frameworks, prompt optimization, fine-tuning workflows, and production-ready LLM applications. ## Key Responsibilities * Design, build, and improve LLM-powered applications using RAG, agentic workflows, and AI orchestration frameworks. * Build retrieval pipelines using embeddings, vector databases, hybrid search, reranking, and knowledge indexing. * Develop AI agents capable of tool use, reasoning, planning, workflow automation, and multi-step task execution. * Experiment with prompt engineering, prompt optimization, guardrails, and structured outputs. * Fine-tune or adapt open-source and commercial LLMs * Build evaluation frameworks for LLM quality, hallucination detection, retrieval accuracy, response relevance, latency, and cost. * Work with product and engineering teams to convert business problems into AI solutions. * Deploy LLM applications using APIs, microservices, cloud platforms, and scalable inference systems. * Monitor production AI systems and continuously improve accuracy, safety, reliability, and performance. * Stay updated with the latest advancements in LLMs, RAG, AI agents, and applied generative AI. ## Required Qualifications * Bachelor’s or Master’s degree in Computer Science, Data Science, Machine Learning, AI, Statistics, Engineering, or a related field. * 2+ years of experience in data science, machine learning, AI engineering, or applied NLP. * Hands-on experience building applications using LLMs such as OpenAI, Anthropic, Gemini, Llama, Mistral, Qwen, or similar models. * Strong Python programming skills. * Experience with RAG pipelines, embeddings, vector databases, and retrieval systems. * Experience with at least one framework such as LangChain, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, Haystack, or similar. * Good understanding of machine learning, NLP, model evaluation, and data preprocessing. * Experience working with APIs, databases, cloud services, and production software systems. * Ability to analyze model outputs, debug failures, and improve system quality. ## Preferred Qualifications * Experience with vector databases such as Pinecone, Weaviate, Milvus, FAISS, Qdrant, Chroma, or Azure AI Search. * Experience with cloud platforms such as Azure, AWS, or Google Cloud. * Experience with model serving or inference frameworks such as vLLM, TGI, Triton, Ray Serve, or FastAPI. * Experience building production-grade AI agents, chatbots, copilots, document intelligence systems, or workflow automation tools. * Knowledge of LLM safety, guardrails, prompt injection prevention, and responsible AI practices. * Experience with MLOps, CI/CD, monitoring, observability, and model performance tracking. ## Technical Skills * Python, SQL, APIs, FastAPI * LLMs, NLP, embeddings, RAG, AI agents * Vector databases and search systems * Prompt engineering and LLM evaluation * Fine-tuning and preference optimization * Cloud deployment and scalable AI systems * Data analysis, experimentation, and model monitoring ## Ideal Candidate The ideal candidate is hands-on, curious, and comfortable working in a fast-moving AI environment. They should be able to quickly prototype ideas, evaluate model performance, and convert AI research into practical products. They should understand both the data science side and the engineering side of building reliable LLM applications. ## Nice to Have * Experience in enterprise AI, document processing, customer support automation, search, recommendation, or workflow automation. * Experience building multi-agent systems or tool-using agents. * Experience optimizing LLM cost, latency, and inference performance. * Experience working with structured and unstructured data sources.

Project ID: 40511506