Staff AI Engineer - Remote Work

About the role

In this role, you'll lead backend AI features end to end, owning a component of a larger body of work alongside a Principal Engineer and a tech lead. Staying hands‑on throughout, you'll build LangGraph flows and RAG pipelines while holding evaluation coverage on everything you ship.

Key responsibilities

• Lead and own backend AI features end to end, breaking down and delivering complex work.
• Build and maintain LangGraph agent flows and RAG pipelines over structured and unstructured data.
• Hold evaluation and tracing coverage on shipped AI behavior.
• Stay hands‑on across development phases, building alongside Principal and Senior engineers.
• Unblock Senior engineers in the pod and surface blockers early.

Required profile

• 8+ years of experience in Python.
• Proven experience building, maintaining, and evolving production LLM systems.
• Hands‑on experience with LangChain and LangGraph, including agent flows, tool and skill invocation, and state management.
• Experience building RAG pipelines over structured and unstructured data.
• Experience with LLM evaluation and tracing, including LangSmith, LLM‑as‑judge, and golden datasets.
• 4+ years of experience with React/Next.js and TypeScript.
• Experience with MCP server development against structured databases and data lakes.
• Experience with streaming agent interactions, including LangGraph API and WebSockets.
• Background with CI/CD pipelines and service observability (logging, tracing, SLOs).
• Experience with distributed systems, microservices, and REST/GraphQL on AWS.
• Strong prompt‑engineering skills and advanced English proficiency.

Required skills

• Python
• LangChain
• LangGraph
• React
• Next.js
• TypeScript
• MCP server development
• Structured databases & data lakes
• Streaming agent interactions (LangGraph API, WebSockets)
• CI/CD pipelines
• Logging, tracing, SLOs
• Distributed systems & microservices
• REST & GraphQL
• AWS
• LangSmith
• LLM‑as‑judge
• Golden datasets
• Prompt engineering
• Bedrock or LiteLLM (model gateway)
• Vector databases (Pinecone, FAISS, Qdrant, pgvector)
• Security best practices (AuthN/AuthZ)
• Analytics & data visualization
• ServiceNow or enterprise workflow integration

What we offer

• 100% remote work from anywhere.
• Excellent compensation in USD or local currency.
• Hardware and software setup for home office.
• Flexible hours – create your own schedule.
• Paid parental leaves, vacations, and national holidays.
• Innovative, multicultural environment with top‑tier talent.
• Mentorship, promotions, skill development, and diverse growth opportunities.