Source:
Senior AI Engineer, MapGPT
Mapbox
United States
; United States (whole country)
Publication date: 03/11/2026
Mapbox is the leading real-time location platform for a new generation of location-aware businesses. This role is scoped by skill rather than by product. The problems span Search and Places data work, Location and Navigation Intelligence work, and the Platform work that makes Mapbox usable by agents. You'll be hired into one specific team or product area, but you'll work across teams where your expertise meets the highest-priority AI problems.
Responsibilities
Define how owned products should work, build a measurement framework, and build evaluation systems for non-deterministic behavior; Run continuous evaluation of products from the end user's perspective, assess gaps, recommend fixes, and ensure they land; Own the MVP against an agreed north star technical design; Build data pipelines and tooling for ingestion, conflation, entity resolution, quality checks, and batch and streaming jobs; Track and evaluate external datasets, models, and benchmarks and decide when to adopt or build; Design feedback loops and instrument systems so failures can be reproduced and turned into evaluation cases; Design the boundary between a model and the tools it calls and build or improve the model harness; Work to latency and cost targets per request; Build internal harnesses and tools (CLI, MCP, and others) 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 rotationRequirements
Bachelor's degree in STEM discipline and 5+ years of software engineering experience, with production ownership of services, pipelines, or SDKs; 2+ years shipping LLM-backed features to real users in systems with error budgets, on-call rotations, and customers who noticed regressions; Data engineering depth: SQL, at least one distributed processing framework, and experience with pipelines where a wrong record mattered more than a slow one; Fluency with tool calling and agent orchestration, including failure modes such as stale context, hallucinated arguments, silent partial success, and unbounded loops; Strong Python or TypeScript, and comfort reading code in whatever language the caller is written in; Direct experience or deep understanding of designing evaluations for non-deterministic systems; Working knowledge of more than one agent harness; Experience diagnosing latency in a distributed request path; Comfort with ambiguity and the judgment to ship something narrow that worksNice to have
Geospatial data experience: routing, geocoding, POI or address data, OpenStreetMap, or conflation of overlapping sources; Public API or SDK design experience; Experience building against MCP or similar tool transports; Experience running evals in CI; Automotive, in-vehicle infotainment, CarPlay, or Android Auto experience; Voice pipeline experience: streaming ASR, TTS, barge-in, endpointing, wake word; Work under constrained compute, offline, or intermittent connectivity; Experience operating a product through its first external integrationsBenefits
Hybrid/Remote options; Comprehensive healthcare with private medical coverage for you and your dependents; Generous maternity and paternity leave; Inclusive fertility support; Lifestyle spending account; Mental health support; Flexible paid time away, company holidays, and generous absence policies; Dedicated paid volunteering time in addition to standard PTO; Retirement plans with competitive matchingHow to apply
Apply online: https://www.jobs.pl/en/oferta/103750195/aplikuj
JOBS.pl · https://www.jobs.pl/en/senior-ai-engineer-mapgpt-oferta-103750195





