Чёткая и значимая backend-роль в быстрорастущей продуктовой компании в сфере AI-инфраструктуры: много самостоятельности и понятные льготы, хотя ответственность за полный цикл и дежурства добавляют нагрузки.
Дежурства в зоне ответственности
Понятная зона задач
Инфраструктура для AI
Щедрые льготы
Выше рынка
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Software Engineer (AI Inference Product) (Backend/Distributed Systems): Building and operating the API layer for hosted model endpoints, including authentication, rate limiting, routing, metering, and billing, with an accent on low latency, reliability, and high-scale inference infrastructure. Focus on designing real-time capacity systems, improving observability, and shipping developer-facing products across a global GPU fleet.
Location: Hybrid in San Francisco or New York, United States
Salary: $200K–$400K plus equity
Company
Baseten provides AI inference infrastructure, hosted model APIs, and developer tooling for companies bringing machine-learning models into production.
What you will do
Build and operate the API layer behind Model APIs, including request handling, authentication, rate limiting, routing, and low-latency high-availability services.
Own real-time usage metering, billing, pricing, and packaging infrastructure.
Design rate-limiting and capacity systems that balance customer throughput with global GPU fleet utilization.
Ship developer-facing API products, including model routing, usage visibility, self-serve controls, and predictable API behavior.
Implement deep observability and alerting, and partner with inference, Model APIs, and product teams to deliver capabilities safely.
Own projects end to end from design through deployment, on-call, and iteration based on customer feedback.
Requirements
Bachelor’s, Master’s, or Ph.D. in Computer Science, Engineering, or a related field, or equivalent practical experience.
3+ years building and operating distributed systems, backend infrastructure, or large-scale APIs with reliability, latency, and scale requirements.
Proven ownership of low-latency, reliable backend services, including rate limiting, authentication, quotas, metering, and migrations.
Infrastructure and performance skills covering profiling, tracing, capacity planning, and SLO management.
Ability to debug performance and reliability issues across application, runtime, and infrastructure layers.
Strong developer-experience focus and interest in how systems are used.
Willingness to learn new languages, frameworks, and systems, with an interest in inference engineering; prior ML or LLM experience is not required.
Excellent written communication and collaboration skills, including design documentation and cross-functional work.
Nice to have
Deep Kubernetes experience, including operators and custom resources, plus service meshes or API gateways.
Experience with distributed scheduling, autoscaling, or service orchestration.
Developer-facing infrastructure or API experience, or contributions to open-source infrastructure or ML systems.
Familiarity with observability tooling, CI/CD systems, or release automation.
Experience with model serving or inference systems.
Culture & Benefits
Meaningful equity and competitive compensation.
For U.S. employees, 100% medical, dental, and vision insurance coverage for employees and dependents.
Flexible PTO and a company-wide Winter Break from Christmas Eve through New Year’s Day.
Paid parental leave and a fertility and family-building stipend through Carrot.
For U.S. employees, company-facilitated 401(k).
Exposure to ML startups and opportunities for learning and networking.
Hiring process
Apply with relevant information demonstrating backend, distributed-systems, and infrastructure experience.
Baseten is an equal opportunity employer and considers qualified applicants with criminal histories consistently with applicable law, including the San Francisco Fair Chance Ordinance where applicable.
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 →