Senior Staff Software Engineer, AI Agent Platform

What you'll do

• Lead the technical design and delivery of major platform components from architecture through rollout and operation.
• Drive design reviews, set engineering standards, and make build-vs-buy decisions for the AI Agent Platform.
• Mentor engineers and raise the engineering bar across the team and the teams building on the platform.
• Build a durable execution engine for agent workflows including state management, checkpointing, and retries.
• Develop a RAG platform for shared ingestion, chunking, embedding, and low-latency retrieval of enterprise data.
• Create an insight engine to transform agent execution data into continuously updated domain knowledge and context.
• Build an eval harness for high-throughput offline and online evaluations to detect regressions and measure quality.
• Own production health by defining SLIs, SLOs, and managing on-call rotations, incident response, and postmortems.

What we're looking for

• 10+ years of professional software engineering experience building and operating large-scale production backend systems.
• Experience owning the design and delivery of significant systems involving multiple engineers or teams.
• Strong proficiency in one or more of Python, Java, Go, or comparable languages.
• Deep distributed systems fundamentals including concurrency, consistency, fault tolerance, data modeling, API design, and scalability.
• Experience operating production services with CI/CD, automated testing, and Kubernetes or other container platforms.
• Hands-on operational experience owning reliability, including observability, monitoring, on-call participation, incident response, and postmortems.
• Proven experience scaling systems by defining SLOs, capacity planning, performance tuning, and eliminating recurring failure modes.
• Experience with durable execution, event-driven architectures, GenAI applications, RAG systems, or evaluation frameworks (preferred).