Lead the architecture and execution of advanced LLM-driven systems, including prompt engineering pipelines, evaluation frameworks, RAG workflows, and LangChain-based orchestration.
Requirements
- Advanced knowledge of prompt engineering strategies and heuristics
- Proficient with LangChain (or similar), Python and API development
- Solid experience building RAG pipelines with vector DBs
- Strong analytical mindset with an A/B testing and evaluation-driven approach
Responsibilities
- design and test prompts for style, tone, and accuracy
- implement rigorous A/B and statistical evaluation frameworks
- deploy LLM-powered features into production
- building retrieval-augmented generation (RAG) pipeline
- developing prompt evaluation systems using PromptEval or similar tools
- orchestrating LLM workflows with LangChain
- optimize prompt performance and user experience in real-world systems
Other
- work cross-functionally with ML engineers, product managers, and backend teams
- deliver scalable, prompt-driven solutions for enterprise applications
- blend of deep prompt engineering expertise, practical Python development skills, and a strong analytical mindset
