Senior AI Engineer, MapGPT

Key details

• Own the technical design and delivery of a multi-component AI system, accountable for the quality of what ships in your area
• Define how owned products should work, build measurement frameworks, and build evaluation systems for non-deterministic behavior
• Formulate hypotheses, validate them with data, define correct results for given inputs and states, and gate changes on regression results
• Own the MVP against an agreed north star technical design, balancing technical perfection against shipping useful increments
• Build data pipelines and tooling: ingestion, conflation, entity resolution, quality checks, and batch and streaming jobs
• Track and pull external datasets, models, and benchmarks from published research and open-source releases; evaluate fit and decide build vs adopt
• Design feedback loops so product usage generates data that improves the product; instrument systems for reproducible failures and turn recurring ones into evaluation cases
• Design the boundary between a model and the tools it calls; build or improve the model harness and decide delegation and state handling
• Work to latency and cost targets per request: streaming, partial results, caching, model routing, prompt structure
• Build internal harnesses and tools (CLI, MCP, and others) for fast iteration and share generalizable parts with other teams
• Raise the bar through code and design review and bring other engineers up on eval practice
• Participate in an on-call rotation to ensure systems remain available 24/7, including possible immediate response outside normal working hours and weekends
• Company mission
• Information not specified