Principal AI Engineer
Core
Design, build, and deploy autonomous multi-agent workflows and enterprise-grade generative AI solutions to enhance employee productivity and streamline information access.
Role type
Principal AI Engineer (Generative AI & Agentic Workflows)
Builds
Production-grade autonomous agent systems, multi-agent orchestration frameworks, and scalable GenAI-powered applications.
Domain
Life Sciences / Enterprise Generative AI
Deliverable
production ML models
Required skills
Agentic orchestration frameworks (LangGraph, CrewAI, Autogen), Cloud LLM providers (AWS Bedrock, Azure OpenAI, Anthropic, OpenAI), Async Python (FastAPI), Docker, CI/CD, Cloud platforms (AWS, Azure, GCP), Model Context Protocol (MCP), LLMOps, Prompt engineering at scale
Preferred skills
Life sciences domain experience, Managing offshore technical teams, Experience with ReAct/Plan-and-Execute patterns
Technologies
LangGraph, CrewAI, Autogen, FastAPI, PostgreSQL, Redis, AWS Bedrock, Azure OpenAI, Anthropic Claude, OpenAI GPT-4, Langfuse, LangSmith, Server-Sent Events (SSE), WebSocket
Responsibilities
Design and deploy autonomous multi-agent workflows with complex state machines; Architect graph-based agent workflows with 10+ nodes; Develop reusable agent node libraries and testing frameworks; Build production-grade FastAPI applications with async I/O; Implement real-time agent streaming and API architectures; Integrate cloud-based LLM providers and prompt management systems; Implement conversation state persistence and tool-calling protocols; Develop hybrid intelligence patterns combining LLM reasoning with rule-based logic; Integrate observability platforms for tracing and cost optimization; Implement evaluation frameworks for agent success and accuracy; Ensure enterprise security integration and compliance; Mentor junior engineers on async Python and LLMOps best practices.
Seniority
Principal, hands-on IC with mentorship
