Staff Engineer, AI Productivity
Staff-level engineer building infrastructure, tooling, and documentation to make AI coding agents dramatically more productive across the codebase. Owns agentic dev environments, MCP integrations, and agent context.
Responsibilities
- Own the agentic development environment: Ensure agents can operate in independent cloud-based development environments, execute full test suites, examine build results visually
- Build tooling integrations: Build MCP server integrations that connect agents to systems needed to build and debug software (CircleCI, Slack, Datadog, Github, etc.)
- Documentation and context: Own repo-wide agents.md file and work with teams to ensure library of agent guidance and skills is continually pushing the bar; ensure conventions and package structures are exposed in ways agents can effectively use
- Enablement: Work with engineers to understand where agents are struggling and address root causes such as better docs, tooling access; develop tooling for non-engineers to make simple visual updates to the application
- Serve as a "PM" for internal AI agents: Stay abreast of state-of-the-art AI productivity trends and drive improvements across the organization
Requirements
- Strong software engineering fundamentals—you can dive into complex backend code and understand it quickly
- Deep hands-on experience with AI coding agents (Claude Code, Cursor, Copilot, Devin, or similar)
- Experience writing effective agent documentation, custom instructions, or context files that meaningfully improved agent output
- Track record of building developer tools or infrastructure that other engineers actually use
- Comfortable working across the stack: CI/CD, cloud infrastructure, internal tooling, and application code
Nice to Have
- Experience building or contributing to MCP servers or similar agent-tooling integrations
- Background in developer productivity, platform engineering, or developer experience roles
- Experience with TypeScript/JavaScript monorepos, Go, GraphQL
- Experience setting up sandboxed or containerized development environments at scale
Senior Network & Site Reliability Engineer
Design, operate, and automate the global network and reliability layer for a high-performance NVIDIA DGX SuperPOD supporting ML workloads. Own architecture, observability, incident response, and security for mission-critical infrastructure.
Senior Data Engineer, Sentinel (Pacific Time Zone)
Senior Infrastructure Engineer building and operating AWS cloud infrastructure for healthcare data platform. Requires Python, Terraform, CI/CD expertise, and big data tools experience.
Senior Software Engineer - Observability Visibility
Senior engineer building observability and resilience standards, tooling, and automation to make reliability the default across Datadog services. Requires 5+ years experience, Go/Python skills, and AI feature delivery experience.
Senior Manager, DevOps Engineering
Lead and mentor a team of DevOps and Infrastructure Engineers responsible for build pipelines, CI/CD systems, developer tooling, and release infrastructure across Hivemind Solutions. Drive modernization of C++/Python build ecosystems and ensure scalable, secure software delivery pipelines.
Software Engineer, Developer Experience
Build internal AI tools and autonomous agents that embed into Retool's engineering workflows to boost developer productivity and reduce toil. Requires shipping real AI-powered developer tools and infrastructure.