Python developer specializing in Retrieval-Augmented Generation (RAG) systems to build, integrate, and optimize LLM workflows. The role focuses on LangChain-based RAG pipelines, vector database integration (e.g., Qdrant), and AWS-based microservices (Lambda, ECS) in containerized environments. Responsibilities also include API/backend development with FastAPI/Uvicorn and implementing monitoring/observability with Datadog tooling. Key Responsibilities
Design and deploy LLM-driven RAG workflows using LangChain and vector databases for high-accuracy retrieval and content generation
Integrate and manage vector databases (e.g., Qdrant) for high-speed vector search and retrieval
Build serverless architectures and scalable containerized applications using AWS services (Lambda, ECS)
Build APIs using FastAPI and Uvicorn to support low-latency interactions and high traffic volumes
Implement observability best practices using Datadog, ddtrace, and logging tools to maintain performance and troubleshoot workflows
Required Qualifications
Minimum 6 8 years of experience (Python/RAG-focused role)
Experience with LLM and RAG workflows using LangChain and vector databases
Advanced Python skills with asynchronous programming