Description

You will construct, optimize, and deploy production-ready Generative AI features and multi-agent workflows.

This role is remote.

Responsibilities

• Develop and iterate on complex agentic workflows using frameworks like LangGraph, AutoGen, CrewAI, or LlamaIndex.
• Build and maintain high-performance Retrieval-Augmented Generation (RAG) systems with hybrid search and re-ranking.
• Expose LLM applications via clean, low-latency REST/gRPC APIs (FastAPI, Node.js) and integrate them into backend microservices.
• Design advanced prompt chains, evaluate LLMs, and optimize for latency, token consumption, and model routing.
• Implement continuous evaluation pipelines (RAGAS, TruLens) and operational monitoring (LangSmith, Phoenix, Datadog).

Required Skills

• 5+ years of backend software engineering experience.
• 1.5+ years of hands-on production experience building Generative AI applications and autonomous agents.
• Strong proficiency in Python or TypeScript with solid experience in asynchronous programming and microservice design.
• Hands-on experience with LangChain, LangGraph, LlamaIndex, or AutoGen, along with function-calling/tool-use APIs.
• Experience with vector databases (Pinecone, Qdrant, Milvus, Weaviate, Pgvector) and traditional relational/NoSQL stores.
• Experience deploying containerized applications (Docker, Kubernetes) across AWS, Azure, or GCP.

Preferred Skills

• Experience with multi-agent collaboration patterns and self-reflection mechanisms.
• Familiarity with open-source LLM architectures and optimization techniques.

Key Skills

Education

Any Graduate