Software Engineer - AI Tooling

Role overview Build software that helps developers and AI agents work effectively with a broad developer platform. You will own tools such as agent integrations, skills, and a dashboard assistant, while evaluating new AI capabilities and deciding which are ready for production. The team emphasizes measurement: tools should be assessed against clear baselines and quality signals so changes improve agent performance rather than introduce regressions.

Responsibilities - Develop and improve agent-facing tools, including an MCP server, agent skills, agents, and an assistant experience. - Make new product capabilities accessible to agents by creating supporting tools, structured knowledge, and evaluations. - Build evaluation suites, instrumentation, feedback loops, and quality gates to measure task success, reliability, and cost. - Study how developers and agents use the tools, then improve interfaces, documentation, and product knowledge delivery. - Create reusable patterns that help customers add AI capabilities to their applications, including agent and embedding workflows. - Support contributions from other engineering teams, centralize shared AI logic, and coordinate with infrastructure partners on reliability, authentication, and hosting. - Validate releases with testing, benchmarking, and stress testing where appropriate.

Requirements - At least five years of professional software engineering experience. - Strong TypeScript skills and fluency with the JavaScript ecosystem, including npm, ES modules, bundlers, and compatibility concerns. - Familiarity with current AI tools and agent patterns, with judgment to distinguish durable approaches from short-lived trends. - Experience building developer tools, product interfaces, or platform components used by other engineers. - Experience designing or using evaluation methods for AI quality and task success, including an understanding of baselines, variance, and cost. - Knowledge of Postgres and relational database practices. - Ability to write tests, communicate clearly, collaborate across product, engineering, and documentation teams, and work effectively in an async environment.

Nice to have Experience with vector databases or embeddings, shipped AI features or agents, developer-focused documentation, evaluation and tracing platforms, CI quality gates, open-source maintenance, or multiple product areas.

Benefits and work setup Fully remote and globally distributed, with asynchronous work. Benefits listed include a coworking allowance, equity, a technology budget, health coverage, annual team gatherings, and a professional development allowance.