Staff AI Platform Engineer

Quick Facts

• Role: Staff AI Platform Engineer

Description

Own and build production AI platform infrastructure enabling safe, rapid AI adoption across the organization, including model access/routing, MCP gateway/connectors, agent runtime and orchestration, memory and knowledge infrastructure, evals and observability, and cost controls. Deliver end-to-end components, set technical direction, and collaborate with AI Dev Tooling and Agentic PDLC teams to turn needs into shared primitives. Ensure production reliability and governance for internal and member-facing AI inference.

Responsibilities

• Establish the vision and “paved paths” for AI-native engineering best practices
• Build the agent runtime and orchestration platform (identity, authorization, audit for scheduled/unattended agents)
• Operate MCP gateway and connector infrastructure with secure, managed, auditable access to internal data, APIs, repos, and SaaS
• Support the LLM gateway (authentication, rate limits, token budgets, model access/routing, per-team cost attribution)
• Build eval and regression infrastructure (golden datasets, offline evals, CI hooks, result storage, quality regression alerts)
• Set up observability (prompt/response tracing, cost per request, quality signals, drift detection)
• Partner with Security, Privacy, and Legal for data handling, tenant isolation, and auditability
• Define how product teams run and monitor AI inference at member scale (serving, latency, reliability, provider management)
• Own production outcomes including SLOs, dashboards, deployment pipelines, and incident response
• Enable shared memory, retrieval, and knowledge infrastructure usable by agents
• Provide SDKs, templates, reusable skills, docs, and enable internal adoption
• Mentor engineers on agent architecture and evaluation rigor; write design docs/standards

Requirements

• 8+ years of engineering experience, including 3+ years building platforms or infrastructure used by other engineers
• Production experience with AI systems such as agentic workflows, LLM integrations, retrieval, and evaluation
• Working knowledge of MCP and agent orchestration, including controls for agents accessing internal systems
• Strong backend and cloud fundamentals: distributed systems, APIs, infrastructure as code, reliability and observability
• Experience operating AI inference in production: latency, reliability, provider management, and cost tradeoffs
• Sound judgment on shared platform investments
• Clear written communication through precise design docs and standards

Benefits

• Medical, dental, vision, life, and disability insurance (100% paid for employees)
• Paid parental leave
• 401(k) with company matching
• Mental wellness program and EAP
• Generous time off (flexible PTO, holidays, summer/winter shutdowns)
• Learning & development programs
• Equipment, tools, and reimbursement support for a remote setup
• Free Life360 Platinum Membership and Tile trackers