3 дня назад
Senior AI Engineer (LLM)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior AI Engineer (LLM): Building and operating multi-component AI systems, evaluation frameworks, data pipelines, and agent-tool integrations for Mapbox products with an accent on LLM-backed features, geospatial data, and production reliability. Focus on designing evaluations for non-deterministic behavior, optimizing latency and cost, and delivering reliable APIs, SDKs, and data systems under on-call requirements.
Location: Remote from any city in Germany
Employment: Full-time, 40 hours per week
Company
provides real-time location infrastructure, including navigation, mapping, data, SDKs, and APIs for location-aware businesses.
What you will do
- Own the technical design, delivery, and quality of multi-component AI systems across Search, Places, Location and Navigation Intelligence, and Platform work.
- Define product behavior, measurement frameworks, evaluation systems, datasets, and regression gates for non-deterministic AI features.
- Build and maintain data pipelines for ingestion, conflation, entity resolution, quality checks, and batch or streaming processing.
- Design model-tool boundaries, agent harnesses, feedback loops, internal CLI and MCP tooling, and systems for reproducing failures.
- Optimize request latency and cost through streaming, partial results, caching, model routing, and prompt structure.
- Participate in code and design reviews, mentor engineers on evaluation practices, and join a 24/7 on-call rotation.
Requirements
- Bachelor’s degree in a STEM discipline and 5+ years of software engineering experience with production ownership of services, pipelines, or SDKs.
- 2+ years of shipping LLM-backed features to real users in systems with customers, error budgets, and on-call rotations.
- Strong data engineering skills with SQL, at least one distributed processing framework, and experience where data correctness is critical.
- Fluency with tool calling and agent orchestration, including stale context, hallucinated arguments, partial success, and unbounded-loop failure modes.
- Strong Python or TypeScript skills, experience designing evaluations for non-deterministic systems, and experience diagnosing latency in distributed request paths.
- Must be able to work remotely from Germany.
Nice to have
- Geospatial data experience with routing, geocoding, POI or address data, OpenStreetMap, or conflation.
- Public API or SDK design experience and experience with MCP or similar tool transports.
- Experience running evaluations in CI, automotive or in-vehicle infotainment systems, or voice pipelines.
- Experience with constrained compute, offline or intermittent connectivity, and external product integrations.
Culture & Benefits
- Flexible remote work with the option to work periodically from an applicable office.
- Private health, dental, income protection, and regional statutory benefits.
- Parental leave, family care support, paid time away, company holidays, and volunteering time.
- Lifestyle spending contributions and mental health support for employees and dependents.
- Teaching, learning, diversity, and inclusive collaboration are emphasized.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →