Senior AI Engineer, Location AI
Posted 22hrs ago
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
Senior AI Engineer building LLM-backed evaluation systems, agent tooling, and data pipelines. Improving Mapbox's real-time location platform across Search, Places, Navigation, and developer tools.
Responsibilities:
- Define product behavior, measurement frameworks, and evaluation systems for non-deterministic behavior
- Formulate product hypotheses and validate them with relevant signals
- Define correct results, assemble datasets, and gate changes on regression results
- Continuously evaluate APIs, SDKs, data representations, and reference applications from end-user perspectives
- Identify misuse, integration anti-patterns, and product gaps; recommend and implement fixes
- Own MVP delivery against an agreed technical design while balancing perfection with useful increments
- Build data pipelines and tooling for ingestion, conflation, entity resolution, quality checks, and batch/streaming jobs
- Track and evaluate external datasets, models, benchmarks, published research, and open-source releases
- Design feedback loops and instrumentation to reproduce failures and convert recurring issues into evaluation cases
- Design model/tool boundaries and build or improve model harnesses
- Optimize latency and cost per request through streaming, partial results, caching, model routing, and prompt structure
- Build internal CLI, MCP, and related tools; share reusable components across teams
- Raise engineering standards through code and design reviews and teach evaluation practices
- Help answer unresolved technical questions in the field
- Participate in a 24/7 on-call rotation to maintain system availability
Requirements:
- Bachelor's degree in a 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 customer-visible regressions
- Data engineering depth: SQL and at least one distributed processing framework
- Experience with pipelines where incorrect records matter more than processing speed
- Fluency with tool calling and agent orchestration, including stale context, hallucinated arguments, silent partial success, and unbounded loops
- Strong Python or TypeScript skills
- Comfort reading code in other programming languages
- Experience or deep understanding of designing evaluations for non-deterministic systems
- Ability to describe a dataset built and the failure it caught
- Working knowledge of more than one agent harness
- Experience diagnosing latency in a distributed request path
- Comfort with ambiguity and judgment to ship narrow, functional solutions
- Participation in an on-call rotation, including possible immediate response outside normal working hours and weekends
- Must be able to work remotely from any city in Germany
Benefits:
- Supportive health care
- Parental leave
- Flexible work arrangements
- Environment of teaching and learning
- Private health, dental, and income protection plans tailored to regional statutory benefits
- Family care, maternity and paternity leave policies
- Lifestyle Spending Account contributions supporting health, wellness, and personal growth
- Mental health support for employees and dependents
- Paid time away, company holidays, and generous absence policies
- Dedicated paid volunteering time in addition to standard PTO
- Hybrid/remote flexibility to work from home or periodically from an office where applicable















