Senior Software Engineer II (AI Enablement)

Role overview Join an internal AI enablement platform team as the engineer accountable for the substrate that powers enterprise-wide AI adoption. This is a senior platform role with direct business impact: model routing decisions affect inference spend and performance, while the gateway you build brokers every tool call between agents and production systems. The work spans infrastructure depth with real users, measurable adoption, and a tight loop between design decisions and outcomes.

Responsibilities - Own and extend the Model Context Protocol (MCP) gateway and connector platform, building and hardening integrations with chat, ticketing, data warehouse, BI, CRM, and project management tools while managing authentication, scopes, tenancy, rate limiting, and read/write policy enforcement. - Run the plugin marketplace publishing pipeline including versioning, CI/CD, plugin review, and release hygiene; build shared plugins, skills, hooks, and authoring guides that other teams can adopt independently. - Own platform observability, model-gateway configuration, and cost attribution so adoption, tool-call health, and inference spend roll up by team, workload, and model; build benchmarks and harness evaluations that drive model selection on evidence. - Extend the agent output and collaboration surface into a browsable, searchable, commentable interface with discovery, tagging, engagement instrumentation, expiry, and share notifications. - Serve as a practitioner during office hours and brownbags, mentor engineers on agentic-coding and plugin-authoring patterns, triage inbound requests, and carry on-call for marketplace-published artifacts and gateway availability.

Requirements - Bachelor's or higher degree in Computer Science, Engineering, or a related field. - 5+ years of professional software engineering experience with production ownership of a backend service or developer platform (API gateway, service proxy, SDK/CLI, or internal developer platform), including its auth model, release process, and operational health. - Strong production experience in at least one modern stack (Python, TypeScript/Node, Go, or similar) and modern CI/CD. - Hands-on experience with authentication and authorization for machine-to-machine traffic such as OAuth2, OIDC, M2M credentials, token scoping, and secret management. - Demonstrated experience instrumenting an owned system with metrics, structured logging, tracing, or usage analytics, and using that data to drive decisions. - Direct hands-on experience with one or more agentic coding tools in a production or near-production setting. - Strong written communication, comfortable producing documentation, runbooks, and educational artifacts for engineers who weren't in the room.

Nice to have - Experience authoring or maintaining MCP servers, Claude Code plugins, skills, hooks, or comparable LLM-tooling integrations. - Experience running an LLM gateway or inference proxy in production (LiteLLM, Bedrock, vLLM, or similar), including routing, fallback, caching, quota, and cost attribution. - Experience building evaluation harnesses or benchmarks for LLM systems, including A/B comparison of prompts, tools, or model versions. - Experience operating a package registry, plugin ecosystem, or extension marketplace with publishing pipelines, semantic versioning, compatibility, and deprecation. - Background in healthcare technology or HIPAA-regulated environments, or familiarity with PHI handling, BAA, and data-residency constraints on third-party tooling.