About the role
Responsibilities:
- Build AI agents for resume analysis, candidate search, screening, technical assessments, and job matching.
- Develop workflows using LLMs, retrieval-augmented generation (RAG), tool calling, and Model Context Protocol (MCP).
- Adapt open-source models using supervised fine-tuning and techniques such as LoRA/QLoRA.
- Build data pipelines to clean, deduplicate, and prepare resumes, job descriptions, and assessment data.
- Create evaluations to measure accuracy, relevance, hallucinations, latency, and cost.
- Deploy and monitor production AI services, improving reliability and inference performance.
- Implement safeguards for candidate privacy, data security, and fair evaluation.
- Collaborate with engineering and product teams to turn experiments into working features.
Requirements:
- Strong Python programming and backend API development experience.
- Hands-on experience building and deploying LLM-powered applications.
- Working knowledge of embeddings, vector search, RAG, structured outputs, and tool calling.
- Experience with PyTorch, Hugging Face Transformers, or similar frameworks.
- Understanding of model evaluation, dataset quality, and fine-tuning fundamentals.
- Experience with SQL, Docker, Git, and cloud infrastructure.
- Ability to independently debug problems and deliver production features.