SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Mapbox is seeking a Senior AI Engineer to own the technical design and delivery of multi-component AI systems across Location AI products. This role is scoped by skill rather than product, spanning Search and Places data work, Location and Navigation Intelligence, and Platform work that enables agents to use Mapbox.
You will define how products should work, build measurement frameworks and evaluation systems for non-deterministic behavior, and formulate hypotheses to validate product decisions. You'll run continuous evaluation of APIs, SDKs, data representations, and reference applications from the end-user perspective (developers, agents, consumers), identifying gaps and recommending fixes.
Key responsibilities include owning MVPs against agreed technical designs while balancing perfection against shipping useful increments; building data pipelines with ingestion, conflation, entity resolution, and quality checks; tracking and evaluating external datasets, models, and benchmarks from research and open-source; designing feedback loops so product usage generates improvement data; designing boundaries between models and their tool calls; working to latency and cost targets per request; building internal tools (CLI, MCP) for rapid iteration; raising team standards through code and design review; and participating in on-call rotations to ensure 24/7 system availability.
This is a distributed, asynchronous role where most decisions happen in documents and Slack across time zones.
REQUIREMENTS:
- Bachelor's degree in STEM discipline
- 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 notice regressions
- Direct experience or deep understanding of designing evaluations for non-deterministic systems; ability to describe a dataset built and failure it caught
- Data engineering depth: SQL, at least one distributed processing framework, experience with pipelines where correctness matters more than speed
- Fluency with tool calling and agent orchestration, including failure modes (stale context, hallucinated arguments, silent partial success, unbounded loops)
- Working knowledge of multiple agent harnesses with opinions on their weaknesses
- Strong Python or TypeScript; comfort reading code in any language
- Experience diagnosing latency in distributed request paths
- Comfort with ambiguity and judgment to ship narrow solutions while general solutions remain unclear
- Clear written communication for distributed, document-driven decision-making
NICE TO HAVE:
- Geospatial data experience (routing, geocoding, POI/address data, OpenStreetMap, conflation)
- Public API or SDK design experience for developers you never interact with
- Experience building against MCP or similar tool transports
- Experience running evals in CI with commercial or custom harnesses
- 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 products through first external integrations
