Staff Software Engineer, Frontier Security Team
Core
Lead the design and development of the Agentic Harness and agent evaluation platform for production-grade LLM applications and intelligent agents.
Role type
Staff Software Engineer (AI Infrastructure & Agent Systems)
Builds
Agentic Harness, agent evaluation platform, simulation/replay infrastructure, multi-tenant model services
Domain
Enterprise AI, Agentic Systems, LLM Infrastructure, Security
Deliverable
production ML models | product features | infrastructure
Required skills
Distributed systems architecture, LLM application development, Agent runtime/workflow engine design, Evaluation system design, Python, Systems programming (Java/Go/Rust/TypeScript), Production observability, Technical leadership
Preferred skills
Multi-agent orchestration, Synthetic task generation, Vector search/retrieval systems, Model fine-tuning, Kubernetes/cloud-native infrastructure
Technologies
Python, Java, Go, Rust, TypeScript, Kubernetes, SQL engines, Vector search, LLM APIs
Responsibilities
Architect multi-step AI workflows, Design stable interfaces for tool execution and state management, Build evaluation harnesses and automated graders, Analyze production agent trajectories for failures, Develop offline/online measurements for quality and cost, Build simulation and replay infrastructure, Define technical direction across teams, Mentor engineers
Seniority
Staff, hands-on IC with technical leadership
