Senior AI Infrastructure Engineer

What you'll do

• Own multi-tenant tool layers including isolation, rate limiting, and caller-attribution systems
• Extend A2A interfaces and experiences to enable agents to invoke other agents
• Build and own durable agent runtimes with long-running execution, task lifecycle management, and failure recovery
• Lead evaluation-driven development with automated CI/CD pipelines and regression detection
• Implement progressive discovery strategies for context, tools, agents, and skills
• Design agent harness and orchestration loop with isolated context, shared memory, and multi-agent coordination
• Drive new agentic capabilities from design to launch for customer experiences
• Participate in on-call rotation for production systems and contribute to incident response and reliability improvements
• Partner with internal teams to promote API-first designs for programmatic and agentic consumers
• Contribute to multi-provider LLM abstraction layers
• Facilitate AI office hours and cross-team enablement as internal expert on LLM tooling and agentic patterns
• Author and review technical documentation including design docs, architecture diagrams, and postmortems

Requirements

• 6+ years of software engineering experience, with 1+ years in AI/ML infrastructure, LLM platform engineering, or agentic system development
• Strong Go (Golang) engineering skills; backend systems are Go-first
• Proficiency in Python and SQL
• Production API design and operations experience, including on-call and incident response
• Experience with multi-tenant system design including rate limiting, caller attribution, tenant isolation, and external support surfaces for shared production APIs
• Deep experience with LLM APIs such as Anthropic or OpenAI, including prompt engineering and tool use/function calling
• Practical experience designing agent loops for production systems, including context and state management, prefix caching, and coordinating multi-step task execution
• Experience with MCP or equivalent tool-layer abstractions for AI agents
• Familiarity with A2A protocols and long-running, durable workflows
• Experience building automated test and evaluation suites for LLM-based systems, including golden scenarios, regression detection, and quality gates in CI/CD
• Ability to work across engineering, product, and operations teams to drive alignment and rollout of shared infrastructure
• Ability to produce design documents, postmortems, and system diagrams for technical and non-technical stakeholders

Tech stack

Benefits