Senior Staff Machine Learning Engineer, Agentic Systems

Quick Facts

• Role: Senior Staff Machine Learning Engineer (Agentic Systems)

Description

Own the runtime infrastructure that powers agentic AI agents for real-time enterprise users. You will build and operate systems for agent orchestration, distributed session management, event-driven message pipelines, structured concurrency, observability, and state/caching layers. The focus is on distributed systems engineering that ensures correctness, low latency, and reliable long-running agent sessions.

Responsibilities

• Design and build an agent orchestration engine using a state machine to manage long-running sessions across planning, execution, user interaction, and multiple LLM/tool calls
• Implement distributed session management with lease-based ownership, heartbeat protocols, and checkpointing/crash recovery
• Build an event-driven message pipeline using ordered queues and streaming/real-time transport
• Use structured concurrency to run multiple async tasks per session with fail-fast semantics and graceful cancellation
• Create observability infrastructure with tracing across async boundaries and custom span lifecycle management for long sessions
• Develop caching and state layers using per-org/bot scoped KV stores and configuration hot-reload

Benefits

• Base pay guideline: $201,300–$352,300 plus equity (when applicable) and variable/incentive compensation
• Health plans, flexible spending accounts
• 401(k) with company match
• ESPP, matching donations
• Flexible time away and family leave programs