Staff ML Engineer — AI Agent Platform

GEICO; Palo Alto (CA); On-site; USD 115,000 - 260,000; Full time

Job summary

GEICO is seeking a Staff Machine Learning Engineer for the AI Agent Platform in California to design, implement, and operate scalable backend systems that enable teams to build, test, and deploy AI agents and workflows. The role emphasizes multi-tenant architectures, governance, and robust tooling across the platform.

You will collaborate with data scientists, engineers, and product teams to advance enterprise AI capabilities, introduce standardized protocols, and ensure reliable, observable

Qualifications

• Bachelor’s in CS, Engineering, or related field; advanced degree highly desirable.
• ],
• job_responsibilities_description([

Responsibilities

• Architect scalable multi-tenant backend systems for AI agent workflows, including configuration, data handling, and governance.
• Build an enterprise AI agent skill ecosystem with discovery, versioning, and security workflows.
• Develop production-grade AI agent harnesses including tool dispatch, context management, and fault tolerance.
• Design context engineering systems and memory hierarchies to optimize token usage.
• Develop observability frameworks with OpenTelemetry for telemetry and governance auditing.

Skills

AI/ML systems

Multi-tenant backend

Python/Java/Go

Cloud platforms (AWS/Azure)

Kubernetes

OpenSearch/PostgreSQL/Redis

Docker/Prometheus/OpenTelemetry

LangChain/AI tooling

Education

Bachelor's in CS/Engineering

Advanced degree desirable

Tools

Docker

Prometheus

OpenTelemetry

Kubernetes

Temporal

OpenSearch

PostgreSQL

Redis

Neo4j

LangSmith/Langfuse

Job description

GEICO is seeking a Staff Machine Learning Engineer for the AI Agent Platform in California to design, implement, and operate scalable backend systems that enable teams to build, test, and deploy AI agents and workflows. The role emphasizes multi-tenant architectures, governance, and robust tooling across the platform.

You will collaborate with data scientists, engineers, and product teams to advance enterprise AI capabilities, introduce standardized protocols, and ensure reliable, observable