Found Description
Responsibilities
- Advanced RAG Architecture: Develop and optimize Retrieval-Augmented Generation (RAG) pipelines, focusing on retrieval quality and context relevance.
- Agent Orchestration: Build complex cognitive flows and decision graphs using LangChain and LangGraph.
- Retrieval Engineering: Manage and optimize vector databases (with emphasis on LanceDB), ensuring efficient searches via embeddings.
- Model Integration: Implement and fine-tune integrations with cutting‑edge LLMs (OpenAI, Claude, Mistral), balancing cost, latency, and quality.
- AI Infrastructure: Maintain scalable solutions on AWS, using Lambdas for asynchronous processing and S3 for large data volumes.
- Strategic Evolution: Translate business needs into viable AI solutions and actively contribute to defining the team’s technical roadmap.
Requirements
- Strong command of Python (focus on performant, clean code).
- Hand...