Machine Learning Engineer (Mapping)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Machine Learning Engineer (Mapping): Design, train, and deploy machine learning models to automate creation of HD maps for the Driver with an accent on computer vision and generative AI techniques. Focus on advancing state-of-the-art methods like Vision-Language Models, owning the full model development lifecycle from data processing to productionization, and collaborating with perception teams.
Location: Onsite in Mountain View, California
Salary: $204,000—$259,000 USD
Company
Autonomous driving technology company building the Driver for fully autonomous ride-hail service and other vehicle platforms.
What you will do
- Design, train, and deploy ML models to automate HD map creation at scale.
- Apply state-of-the-art techniques including Vision-Language Models and Generative AI for mapping solutions.
- Own end-to-end model lifecycle: data mining, processing, training, evaluation, validation, and productionization.
- Collaborate with Perception and AI Foundations teams to integrate research into production systems.
Requirements
- 4+ years hands-on experience in Machine Learning, focused on computer vision and/or deep learning.
- Proficiency in at least one deep learning framework (TensorFlow, PyTorch, JAX).
- Experience owning problems end-to-end across systems stack.
- B.S. in Computer Science or equivalent practical experience.
Nice to have
- M.S. or Ph.D. in Computer Science or related field.
- Familiarity with foundation models and adaptation techniques (few-shot learning, transfer learning).
- Publications in top ML/CV conferences (NeurIPS, ICML, CVPR).
- Experience with C++.
- Direct experience with mapping or GIS.
Culture & Benefits
- Discretionary annual bonus program.
- Equity incentive plan.
- Generous company benefits program.
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 →