Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Staff Software Engineer (AI): Building and optimizing high-scale LLM inference infrastructure for enterprise customers with an accent on reliability, latency, and efficiency. Focus on distributed AI workloads, GPU orchestration, and developing seamless end-to-end model serving experiences.
Location: San Francisco, California
Salary: $190,000 — $265,000 USD
Company
Databricks is a data and AI company providing a Data Intelligence Platform to unify data, analytics, and AI for over 10,000 organizations worldwide.
What you will do
- Build LLM infrastructure powering large-scale inference workloads using both partner and self-hosted models.
- Improve the reliability, latency, and efficiency of distributed AI workloads.
- Collaborate with platform, infrastructure, and ML teams to deliver seamless end-to-end experiences.
- Shape how developers and data scientists build and interact with AI on the Databricks platform.
Requirements
- 8+ years of experience in backend or infrastructure engineering.
- Experience with distributed systems, scalable APIs, or cloud-native infrastructure.
- Experience with real-time serving, ML infrastructure, or GPU orchestration.
- Familiarity with service-oriented architecture, deployment pipelines, and system observability.
Nice to have
- Exposure to platforms like SageMaker, Vertex AI, or Azure ML.
- Contributions to OSS projects such as MLflow, PyTorch, Ray, vLLM, or SGLang.
- Experience building developer platforms or internal tools supporting AI workflows.
Culture & Benefits
- High-agency, high-visibility team operating at the frontier of AI infrastructure.
- Engineering-led culture focused on solving the world's toughest technical challenges.
- Comprehensive benefits and perks tailored to employee needs across different regions.
- Strong commitment to diversity, inclusion, and equal opportunity employment.
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 →