Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
Очень мало
$100к-150к/год
$140к$180кмедиана$220к
По похожим ролям (47) ~ $180к/год
На СНГ рынке: $4.1к/мес ($3.6к - $4.7к)
60
Средняя вакансия
развернуть
Вакансия даёт серьёзные практические задачи в быстрорастущей области AI-систем, но зарплата заметно ниже рыночного ориентира, а консалтинговый формат может ограничивать влияние на проект.
Кликните для подробной информации
Ниже рынкаКонсалтинговый форматПередовые технологииПонятные задачи
Оценка от Hirify AI
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
ML Performance Engineer (AI): Optimizing end-to-end training and inference pipelines for large neural network systems with an accent on GPU performance, distributed training, memory management, and compiler-level optimization. Focus on reducing latency and cost, tuning LLM serving with quantization and KV cache techniques, and building rigorous benchmark and regression frameworks.
Location: 100% remote within the United States. The posting also lists South Jordan / Draper, Utah.
Salary: $100,000–$150,000 annually.
Company
hirify.global is a technology consulting and software development company delivering cloud, AI, data, and enterprise solutions across the United States.
What you will do
Profile and optimize end-to-end AI training and inference pipelines for throughput, latency, and cost.
Identify bottlenecks across data loading, model computation, communication, memory, and storage access.
Implement quantization, sparsity, pruning, KV cache optimization, continuous batching, and speculative decoding for efficient LLM serving.
Optimize distributed training with tensor parallelism, pipeline parallelism, FSDP, and ZeRO-style sharding.
Drive compiler and kernel-level improvements using Triton, XLA, TorchInductor, or TVM.
Build benchmark and regression frameworks, evaluate hardware and software, document tuning practices, and collaborate with ML and platform engineering teams.
Requirements
Must be based in the United States; the role is 100% remote within the U.S.
Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field.
Six or more years of experience in performance engineering, ML systems, or HPC.
Strong proficiency in Python and C++, with hands-on experience optimizing deep learning workloads on modern GPUs.
Deep understanding of distributed training and inference, profiling across CPU, GPU, and distributed systems, memory hierarchies, communication primitives, and parallelism.
New H-1B visa petitions cannot be sponsored. U.S. citizens, Green Card holders, EAD holders, and H-1B transfer candidates are encouraged to apply.
Contributions to vLLM, TensorRT-LLM, DeepSpeed, or similar projects.
Custom kernel authoring with Triton or CUTLASS.
FinOps experience for AI workloads.
Publications or talks on AI systems performance.
Culture & Benefits
Full-time direct W-2 employment.
Collaboration with product, design, engineering, operations, and business stakeholders.
Opportunities to mentor junior engineers and contribute to code and design reviews.
Career growth within an established technology consulting and software development organization.
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 →