Влиятельная роль уровня Staff в сфере GenAI с передовым стеком и очень четкими ожиданиями. Зарплата достойная и соответствует рынку.
?Высокий темп
?Рыночная зарплата
Передовой стек
Трендовый домен
Четкие ожидания
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Staff AI Product Engineer (GenAI Inference): Setting technical direction for dedicated and serverless inference, model deployments, post-training services, and the serving platform with an accent on GPU performance, KV-cache orchestration, evaluation, and LLM reinforcement learning. Focus on designing benchmarks and reusable tooling, optimizing kernels and distributed GPU systems, and balancing latency, throughput, cost, and model quality across the inference stack.
Location: Houston, New York, San Francisco, or Seattle, United States
Base salary: $220,000–$330,000 USD per year, with potential bonus, equity, and/or commission programs.
Company
Nscale builds a vertically integrated GenAI cloud platform spanning data centers, software, and AI applications.
What you will do
Set technical direction for inference, serving, post-training, evaluation, or GPU performance focus areas.
Resolve systemic performance and reliability issues across APIs, routers, schedulers, serving engines, kernels, and GPU clusters.
Optimize the trade-offs between cost, latency, throughput, and model quality using measurement and benchmarking.
Build reusable frameworks, benchmarks, and tooling for AI engineers.
Evaluate serving engines, kernel libraries, reinforcement-learning frameworks, and accelerators, and recommend whether to build, adopt, or contribute.
Coach engineers and collaborate with research, product, infrastructure, and technical leadership.
Requirements
8–12 years of engineering experience, including significant depth in production AI systems or large-scale ML research.
At least 4 years of hands-on LLM experience in one or more relevant focus areas.
Deep expertise in at least one area such as KV-cache offloading, inference performance, GPU kernels, evaluations, post-training and RL, or serving platforms.
Strong Python and PyTorch skills with experience building maintainable, tested, production-grade systems.
Experience operating AI workloads in containerized, distributed environments, including Kubernetes and large GPU clusters.
Strong understanding of GPU performance, transformer and LLM architectures, and distributed serving systems.
Nice to have
Contributions to open-source inference, kernel, or RL projects such as vLLM, SGLang, TensorRT-LLM, LMCache, Triton, or DeepSpeed.
Experience at an AI lab, hyperscaler AI team, or leading ML infrastructure company.
Published research or technical writing on inference, kernels, evaluations, or reinforcement learning.
Experience with custom kernels, developer-facing APIs and SDKs, or control-plane and data-plane separation.
Culture & Benefits
Fast-paced environment focused on shipping, measurement, and iteration.
Ownership of problems from start to finish, with an emphasis on accountability and technical excellence.
Collaboration across serving, post-training, platform, research, product, and infrastructure teams.
Medical, dental, and vision coverage, flexible paid time off, parental leave, and retirement plan participation.
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 →