Description

You will design and deploy LLM-driven RAG workflows to enable high-accuracy data retrieval and content generation.

This role is on-site.

Responsibilities

• Build and optimize LLM workflows using LangChain and vector databases.
• Integrate vector databases like Qdrant for high-speed search and retrieval.
• Develop scalable containerized applications and serverless architectures using AWS Lambda and ECS.
• Construct low-latency APIs with FastAPI and Uvicorn to handle high traffic volumes.
• Implement observability and monitoring using Datadog, ddtrace, and logging tools.

Required Skills

• 5+ years of software engineering experience.
• Advanced Python skills (version 3.11).
• Proficiency in Gen AI, LLMs, and RAG workflow development.
• Hands-on experience with LangChain and vector databases.
• Experience with AWS services including Lambda and ECS.
• Proficiency in containerization using Docker.
• Experience building backend APIs with FastAPI and Uvicorn.
• Understanding of MCP Servers.
• Knowledge of observability tools like Datadog and ddtrace.

Preferred Skills

• Experience managing vector databases such as Qdrant.

Key Skills

Education

Any Graduate