Staff Machine Learning Engineer, AI Agent Platform
Core
Design, implement, and maintain scalable backend systems and SDKs for an enterprise AI Agent OS, enabling teams to build, test, and deploy AI agents and workflows.
Role type
Staff Machine Learning Engineer (AI Platform & Infrastructure)
Builds
Multi-tenant backend systems, AI agent skill ecosystems, production-grade agent harnesses, and context engineering systems for GEICO's AI Agent Platform.
Domain
Insurance / Generative AI / Agentic AI Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Python, Java, Go, Kubernetes, Temporal, OpenSearch, PostgreSQL, Redis, Neo4j, Docker, Prometheus, OpenTelemetry, TensorFlow, PyTorch, LangGraph, CrewAI, AutoGen
Preferred skills
Harness engineering, AI agent skill system design, MCP (Model Context Protocol) development, A2A (AI Agent-to-Agent) protocols, LLM observability, multi-agent orchestration
Responsibilities
Architect scalable multi-tenant backend systems for AI agent workflows; Build an enterprise AI agent skill ecosystem with versioning and governance; Implement production-grade AI agent harnesses for tool dispatch and error recovery; Develop context engineering systems including memory hierarchies and RAG pipelines; Design layered guardrail architectures for AI safety and governance; Act as tech lead providing mentorship and establishing engineering standards.
Seniority
Staff, hands-on technical leadership