Назад
Company hidden
9 часов назад

Machine Learning Engineer

Формат работы
onsite
Тип работы
fulltime
Грейд
middle
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Machine Learning Engineer (PyTorch/Distributed Training): Productizing and optimizing machine learning models into reliable, performant, and cost-efficient training and serving systems with an accent on distributed GPU training, inference optimization, and scalable model serving. Focus on building low-latency services, improving throughput and time-to-train, implementing quantization and memory-efficiency techniques, and maintaining production observability and cost KPIs.

Location: San Jose, CA, United States

Company

hirify.global.

What you will do

  • Productize and optimize research models into reliable, performant, and cost-efficient production services with clear latency, availability, and cost SLOs.
  • Scale training across nodes and GPUs using distributed training and parallelism techniques, while optimizing throughput and time-to-train through profiling.
  • Implement model-efficiency methods including quantization, distillation, pruning, KV-cache optimization, and Flash Attention for training and inference.
  • Build and maintain model-serving systems with batching, streaming, caching, autoscaling, load balancing, and memory management.
  • Integrate vector and feature stores with production data pipelines and storage systems.
  • Track performance and cost KPIs, plan capacity, and collaborate with ML Ops, Scientists, Platform/Infra, Data, and Product functions on deployment, observability, registries, handoffs, and evaluations.

Requirements

  • Bachelor’s degree in computer science, electrical/computer engineering, or a related field; equivalent industry experience is also accepted.
  • 3–5 years of experience in ML/AI engineering roles owning training and/or serving in production at scale.
  • Strong systems and ML engineering experience with exposure to distributed training and inference optimization.
  • Experience delivering high-throughput, low-latency ML services with reliability and cost improvements.
  • Experience collaborating across Research, Platform/Infra, Data, and Product functions.
  • Familiarity with PyTorch as the primary deep learning framework and TensorFlow.
  • Experience or exposure to DDP, FSDP, ZeRO, pipeline parallelism, and tensor parallelism.
  • Experience profiling and optimizing code execution and model inference, including PTQ/QAT/AWQ/GPTQ, pruning, distillation, KV-cache optimization, and Flash Attention.
  • Knowledge of scalable serving, SQL/NoSQL, vector stores, Parquet/Delta, object stores, performant maintainable code, and the full ML lifecycle from data collection through evaluation.

Nice to have

  • Master’s degree in computer science, electrical/computer engineering, or a related field.
  • Distributed training experience.

Culture & Benefits

  • Collaborate with Research, ML Ops, Platform/Infra, Data, and Product functions.
  • Own measurable improvements in reliability, throughput, latency, capacity, and cost.

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 →