В Google DeepMind это чётко очерченная роль на стыке production AI, робототехники и model serving, с сильной исследовательской средой и серьёзными техническими задачами.
?Высокий порог входа
Современный AI-стек
Сильная AI-среда
Понятная зона ответственности
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Software Engineer, Agentic Model Serving, Robotics, DeepMind (AI): Building reliable, low-latency model-serving and deployment systems spanning on-robot runtimes, edge compute, and cloud infrastructure with an accent on robotics foundation-model inference, bidirectional streaming, and real-time control. Focus on profiling the sensory-to-action loop, optimizing accelerator inference and KV-cache management, and co-designing agentic harnesses and deployment workflows.
Location: Mountain View, CA, USA
Salary: $174,000–$252,000 USD annually, plus 15% bonus target, equity, and benefits.
Company
Google DeepMind is an AI research lab developing technologies for scientific discovery, public benefit, and high-quality products, with a focus on safety and ethics.
What you will do
Architect reliable and scalable model-serving and deployment systems across on-robot runtimes, local edge compute, and cloud backends.
Customize systems for stateful bidirectional streaming, multi-rate agentic control loops, and fast model hot-swapping in robotics deployments.
Analyze, profile, and optimize the full sensory-to-action pipeline, including sensor ingestion, transport, real-time execution, KV-cache management, graph compilation, and accelerator inference.
Co-design agentic harnesses, streaming APIs, and closed-loop deployment workflows with research scientists, hardware and control engineers, and partner teams.
Design, develop, test, deploy, maintain, and enhance software while managing project priorities, deadlines, and deliverables.
Requirements
Bachelor’s degree or an advanced degree.
4 years of experience in software development.
Production experience with Large Language Models or Vision-Language Models.
Experience optimizing model inference performance on hardware accelerators such as TPUs and GPUs.
Experience with machine-learning frameworks, particularly JAX or TensorFlow, focused on inference and serving.
Nice to have
Experience developing or integrating Google production model-serving solutions such as Beyond and Uniserve.
Experience integrating security best practices into ML infrastructure.
Expertise building, profiling, and optimizing complex, highly available, secure software systems for end-to-end performance.
Familiarity with robotics software stacks and experience taking complex technical features from design through production deployment.
Strong, proven programming skills in Python and C++.
Culture & Benefits
Work with interdisciplinary AI research, engineering, hardware, and partner teams.
Opportunities to work across projects and career pathways as the business evolves.
15% bonus target, equity, and Google benefits.
Safety, ethics, scientific discovery, and broad public benefit 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 →