Description

You will build and deploy production-grade AI agents and multi-agent systems, developing RAG-based applications and integrating LLMs.

This role is hybrid.

Responsibilities

• Build secure FastAPI microservices to support AI agents and distributed systems.
• Implement agent tools, MCP integrations, and evaluation frameworks for reliability and cost optimization.
• Develop RAG pipelines including ingestion, chunking, embeddings, hybrid search, and citations.
• Participate in code reviews, architecture discussions, and CI/CD practices.

Required Skills

• 5+ years of experience in software development or data engineering.
• Strong Python (FastAPI, Async, Pydantic) or Node.js/TypeScript.
• Hands-on experience with at least one agent framework: LangGraph, Claude Agent SDK, LangChain, AutoGen, CrewAI, or Semantic Kernel.
• Experience building Generative AI/LLM applications using OpenAI, Azure OpenAI, Anthropic, or AWS Bedrock.
• Strong experience implementing RAG pipelines and vector databases such as pgvector, FAISS, or OpenSearch.
• Experience developing REST APIs, microservices, and distributed systems.
• Knowledge of PostgreSQL, Amazon S3, Docker, Git, CI/CD, and AWS.
• Experience with tool/function calling, structured outputs, streaming, and MCP integrations.

Preferred Skills

• Familiarity with AI evaluations, guardrails, hallucination detection, and prompt injection protection.

Key Skills

Education

Bachelor's or Master's degrees