Staff Engineer – AI Platform

• Architect and build production-grade agentic systems for platform automation and internal engineering workflows
• Build a shared AI platform with reusable agent frameworks, tool and MCP integrations, an LLM gateway, and prompt/model versioning
• Establish evaluation and observability for AI systems, including eval harnesses, agent-run tracing, and quality, latency, cost, and safety metrics
• Drive AI-assisted developer workflows and automation of operational toil
• Manage GCP/AWS cloud infrastructure for AI workloads, including provisioning, scaling, security, and cost governance
• Own and evolve reliable, extensible, and performant agentic-system architecture
• Establish guardrails, scoped permissions, sandboxing, prompt-injection defenses, audit trails, graceful degradation, and incident-management practices
• Establish offline evaluations, regression suites, and production monitoring
• Optimize inference, token, and infrastructure costs
• Set technical standards, lead design reviews, mentor engineers, and promote AI engineering craftsmanship
• Partner with product engineering, SRE/infra, security, and leadership teams
• Communicate technical direction, risks, and progress across the organization

• 12+ years of overall software engineering experience, including significant time as a senior or staff-level individual contributor
• At least the last 1+ year spent architecting agentic systems in production
• Experience designing multi-step, tool-using agents, orchestration, memory and context management, and guardrails
• AI-first mindset and active use of AI tools in engineering workflows
• Expert-level proficiency in Go, Python, or Node.js
• Strong hands-on coding, code review, production debugging, and architecture experience
• Strong working knowledge of tool/function calling, MCP, retrieval and context engineering, prompt and model management, and evaluation methodologies
• Deep AI observability experience using Prometheus, Grafana, ELK/OpenSearch, or equivalent
• Strong understanding of distributed systems architecture
• Track record of measurable cost optimization in an enterprise cloud environment
• Practical experience with GCP and/or AWS service management, including provisioning, scaling, IAM, networking, and cost governance
• At least 3+ years of individual-contributor experience on platform teams at enterprise scale
• Ability to lead technically without authority, write design documents, drive cross-team alignment, and mentor engineers
• Data-driven approach to decision-making, prioritization, and performance reporting
• Excellent verbal and written communication skills
• Open-source contributions or published work on agentic systems are a plus

• Global, remote-first organization
• Opportunity to work on AI-driven capabilities at enterprise scale
• Technical mentorship and leadership opportunities
• Open-source contributions or published work on agentic systems considered a plus