M

Mapbox

Geospatial mapping SDKs and APIs provider

Senior AI Engineer - Location AI

AI Application Engineering +1Confirmed live in the last 24 hours
Full-timeRemote in UKNo salary listed

About the Job

Requirements

  • A bachelor's degree in a STEM discipline and at least 5 years of software engineering experience, including production ownership of services, pipelines, or software development kits.
  • At least 2 years of experience shipping large language model-backed features to real users in systems with error budgets, on-call rotations, and customers affected by regressions.
  • Direct experience or deep understanding of designing evaluations for non-deterministic systems, including the ability to describe a built dataset and the failure it caught.
  • Data engineering depth, including SQL, at least one distributed processing framework, and experience with pipelines where incorrect records have greater impact than slow processing.
  • Fluency with tool calling and agent orchestration, including failure modes such as stale context, hallucinated arguments, silent partial success, and unbounded loops.
  • Working knowledge of more than one agent harness and opinions about their limitations.
  • Strong Python or TypeScript skills and comfort reading code in other languages.
  • Experience diagnosing latency in a distributed request path.
  • Comfort working with ambiguity and judgment to ship a narrow solution while the general solution remains unclear.
  • Clear written communication for a distributed, document- and Slack-based work environment.
  • Ability to participate in an on-call rotation, including immediate response outside normal working hours and on weekends.

Responsibilities

  • Define how owned products should work, build measurement frameworks and evaluation systems for non-deterministic behavior, formulate hypotheses, define correct results, determine how to assemble datasets, and gate changes on regression results.
  • Continuously evaluate APIs, software development kits, data representations, and reference applications from the perspective of developers, agents, and consumers; identify issues such as parameter misuse and integration anti-patterns, recommend fixes, and ensure they are implemented.
  • Own the minimum viable product against an agreed technical design and balance technical perfection with shipping useful increments.
  • Build data pipelines and supporting tooling for ingestion, conflation, entity resolution, quality checks, and batch and streaming jobs that keep large datasets current.
  • Track and retrieve external datasets, models, and benchmarks from published research and open-source releases; evaluate their fit and decide whether to adopt existing options or build alternatives.
  • Design feedback loops so product usage generates improvement data; instrument systems to provide sufficient failure context for reproduction and convert recurring failures into evaluation cases.
  • Design the boundary between a model and the tools it calls; build or improve the model harness, determine what the model handles or delegates, and ensure it operates on the state it actually retrieved.
  • Meet per-request latency and cost targets using techniques such as streaming, partial results, caching, model routing, and prompt structure.
  • Build internal harnesses and tools, including command-line interfaces and Model Context Protocol tools, and share reusable components with other teams.
  • Improve the team's work through code and design reviews and help other engineers learn evaluation practices.
  • Help answer unresolved technical questions in this area.
  • Participate in an on-call rotation to maintain system availability for customers around the clock, alternating as the primary responder.

Desired Qualifications

  • Geospatial data experience, including routing, geocoding, points of interest or address data, OpenStreetMap, or conflation of overlapping sources.
  • Public application programming interface or software development kit design experience, particularly for developer users.
  • Experience building against Model Context Protocol or similar tool transports.
  • Experience running evaluations in continuous integration, using a commercial harness or a self-built harness.
  • Automotive, in-vehicle infotainment, CarPlay, or Android Auto experience.
  • Voice pipeline experience, including streaming automatic speech recognition, text-to-speech, barge-in, endpointing, or wake words.
  • Experience working with constrained compute, offline operation, or intermittent connectivity.
  • Experience operating a product through its first external integrations, where customers identify gaps.

About the Company

Mapbox

Geospatial mapping SDKs and APIs provider

Mapbox provides customizable geospatial mapping and location services for developers, businesses, and government agencies through a suite of APIs and SDKs. Its Maps SDKs embed custom maps in web and mobile apps; Navigation SDKs offer turn-by-turn routing; Vision SDKs interpret road scenes via device cameras; Traffic Data powers routing and analytics; Mapbox Boundaries visualizes global polygons; Movement analyzes where and when people move; Atlas lets clients run Mapbox on their own infrastructure offline or behind a firewall. The product works by developers integrating these SDKs/APIs into their apps to add maps, navigation, and location features, with usage- and subscription-based pricing. Mapbox differentiates itself with a broad, modular toolkit for geospatial features, strong offline/on-premises options, and a clear B2B focus. Its goal is to enable scalable, customizable location services for apps and services worldwide.

Company size
501-1,000
Company stage
Growth Equity (Venture Capital)
Total funding
$614.2M
Headquarters
Washington DC, District of Columbia
Founded
2011

Recently Posted Jobs

Explore more opportunities at Mapbox

See more jobs