Mapbox

Overview

We are seeking a Senior AI Engineer to own the technical design and delivery of a multi-component AI system, working across teams where expertise meets high-priority AI problems.

About Mapbox

Mapbox is the leading real-time location platform for a new generation of location-aware businesses. Mapbox is the only platform that equips organizations with the full set of tools to power the navigation of people, packages, and vehicles everywhere. More than 4 million registered developers have chosen Mapbox because of the platform’s flexibility

Requirements & Eligibility

• Bachelors 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 that carried error budgets, on-call rotations, and customers who noticed regressions
• Direct experience or deep understanding of designing evaluations for non-deterministic systems
• Data engineering depth: SQL, at least one distributed processing framework
• Fluency with tool calling and agent orchestration
• Working knowledge of more than one agent harness
• Strong Python or TypeScript
• Experience diagnosing latency in a distributed request path

Key Responsibilities

• Define how the products you own should work, build a measurement framework for it, and build evaluation systems for non-deterministic behavior
• Run continuous evaluation of the products we build, whether APIs, SDKs, data representations, or reference applications
• Own the MVP against an agreed north star technical design, and balance technical perfection against shipping useful increments
• Build data pipelines and the tooling around them: ingestion, conflation, entity resolution, quality checks, and batch/streaming jobs
• Track and pull external datasets, models, and benchmarks from published research and open-source releases
• Design feedback loops so that using a product generates data that improves it
• Design the boundary between a model and the tools it calls
• Work to a latency and cost target per request