Staff Machine Learning Engineer, AI Agent Platform
AI Tools
Tech Stack
Agent Workflow
Build the next generation enterprise AI Agent OS and SDKs. Design multi-tenant backend systems for agentic workflows, build AI agent skill ecosystem, implement production-grade agent harnesses with tool dispatch, context management, error recovery. Develop context engineering systems including memory hierarchies, RAG pipelines, and scratchpads.
About the Role
GEICO seeks a Staff ML Engineer to architect the enterprise AI Agent OS and SDKs. You will design, implement, and maintain scalable backend systems that enable business, product, and engineering teams to build, test, and deploy their own AI agents and workflows.
Key responsibilities include designing multi-tenant backend systems for agentic workflows using AKS and FastAPI, building an AI agent skill ecosystem with discovery, versioning, and governance controls, implementing production-grade agent harnesses (tool dispatch, context management, error recovery), developing context engineering systems including memory hierarchies (short-term, working, long-term), RAG pipelines, and scratchpads, and creating observability frameworks with LLM-specific telemetry.
You will also design layered guardrail architectures for prompt injection defense and PII detection, and implement skill-level security vetting.
Requirements: 6+ years building multi-tenant AI/ML systems in production. Experience with Azure, AWS, Kubernetes, Temporal, OpenSearch, PostgreSQL, Redis, Neo4j. Proficiency in Python, Java, or Go. Experience with TensorFlow, PyTorch, LangGraph, CrewAI, AutoGen. Docker, Prometheus, OpenTelemetry expertise.
Preferred: Harness engineering and MCP/A2A protocol experience. LLM observability tools (LangSmith, Langfuse, Arize Phoenix). Multi-agent orchestration experience.
Salary: $115,000 - $260,000.
