machine learning engineer for inference

Inworld

United States

Remote

USD 186,000 - 266,000

Full time

9 days ago

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Job summary

Inworld — исследовательская лаборатория и платформа инференса, работающая над реал-тайм ИИ для потребительских приложений. Мы разворачиваем сервисы и API для больших нагрузок, стремимся к минимальным задержкам и максимальной производительности.

Вам предстоит контейнеризовать модели, оптимизировать их под продакшн и строить устойчивые решения, развиваться в рамках сложной архитектуры и делиться результатами с сообществом.

Qualifications

  • Глубокое понимание современных серверных фреймворков и методик (vLLM, TRT-LLM).
  • Практический опыт квантования, дистилляции, кэширования, батчинга и paged attention.
  • Отличное владение C++, CUDA, Rust или высоко оптимизированным Python.
  • Умение профилировать код и оптимизировать на NVIDIA GPUs.
  • Опыт работы с Kubernetes, Ray, балансировкой нагрузки и многопроцессорным инференсом.
  • PhD или эквивалентный опыт в backend/ML системах.
  • Способность быстро учиться, работать независимо и пробовать новые направления.
  • Ориентация на релиз стабильных решений и реальное влияние.

Responsibilities

  • Взять модели с исследовательской команды, контейнеризовать их и оптимизировать сервис.
  • Писать стабильные инженерные решения с акцентом на влияние, а не на теорию.
  • Улучшать архитектуры для снижения задержек и повышения пропускной способности.
  • Разрабатывать бенчмарки и прототипы для изучения неопределённых задач.
  • Считать производительность, задержки и надежность важнейшими характеристиками продукта.
  • Делиться результатами и вносить вклад в open source.

Skills

Сервинг фреймворки / vLLM
Квантизация и дистилляция
Оптимизация Python/C++/Rust
Профилирование на NVIDIA GPU
Kubernetes и Ray
Масштабируемый инференс (мульти-узлы)
Практический опыт ML backend
Гибкость к обучению и самостоятельная
Увлеченность решением сложных архитект
Open-source в инференс

Education

PhD в CS, физике или математике

Tools

Kubernetes
Ray
vLLM
TRT-LLM

Job description

Описание:

Inworld is a research lab and inference provider focused on real-time AI for consumer-facing applications. It builds speech models, serves LLMs, and provides inference through modular APIs for high-volume, real-time workloads.

Задачи:
  • Take models from the research team, containerize them, optimize their serving, and ensure they run reliably in production
  • Ship stable engineering solutions and prioritize impact over theoretical optimizations
  • Question and improve architectures to address latency and throughput challenges
  • Design benchmarks or prototypes to investigate unclear problems
  • Treat performance, latency, and reliability as first-class product features
  • Share work and contribute to open source
Требования:
  • Strong understanding of modern serving frameworks and techniques such as vLLM or TRT-LLM
  • Hands-on experience with quantization, distillation, caching strategies, continuous batching, paged attention, and speculative decoding
  • Proficiency in C++, CUDA, Rust, or highly optimized Python
  • Ability to profile code and optimize performance on NVIDIA GPUs
  • Experience with Kubernetes, Ray, custom load balancing, multi-GPU/multi-node inference, and handling thousands of concurrent connections reliably
  • PhD in CS, Physics, or Math, or equivalent practical experience building backend or ML systems
  • Ability to learn quickly, thrive in ambiguity, choose a direction, and work independently
  • Focus on shipping stable solutions and delivering impact
  • Curiosity about the reasoning behind technical decisions and willingness to challenge architectures
  • Будет плюсом: Non-trivial systems programming projects, open-source contributions to major inference engines, deep-dive technical write-ups
Условия:
  • Base salary range: £140,000 – £200,000
  • Total compensation includes equity and benefits
  • Individual pay within the range depends on work location, level, competencies, experience, and business needs
  • Candidates must already have the legal right to work in the United Kingdom; visa sponsorship is not available
  • Full U.S. visa and relocation support may be available for candidates interested in relocating to the San Francisco Bay Area in the future, subject to business needs and applicable legal and work authorization requirements
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Senior Machine Learning Engineer, Inference
Senior Machine Learning Engineer, Inference

AIDA Recruitment • Mountain View (CA)

On-site
USD 250,000 - 300,000
Relocation assistance
Visa support
Senior Machine Learning Engineer, Inference
Senior Machine Learning Engineer, Inference

AIDA projektai, MB • Mountain View (CA)

On-site
USD 250,000 - 300,000
Senior Machine Learning Engineer, Inference - USA
Senior Machine Learning Engineer, Inference - USA

inworld.ai • Mountain View (CA)

On-site
USD 250,000 - 300,000
Relocation assistance
Staff / Senior Staff Machine Learning Engineer, Inference - UK
Staff / Senior Staff Machine Learning Engineer, Inference - UK

Inworld AI • United States

Remote
USD 188,000 - 269,000
Equity
Benefits
Member of Technical Staff (AI Inference Engineer)
Member of Technical Staff (AI Inference Engineer)

Kindredventures • Palo Alto (CA)

Hybrid
USD 190,000 - 250,000
Comprehensive health insurance
Dental insurance
Vision insurance
+1
Ml engineer in real-time AI inference
Ml engineer in real-time AI inference

Cavendish Professionals • United States

Remote
USD 180,000 - 240,000
Senior Software Engineer - Model Performance
Senior Software Engineer - Model Performance

inference.net • San Francisco (CA)

Hybrid
USD 220,000 - 320,000
Equity in a high-growth startup
Comprehensive benefits
Staff / Senior Staff Machine Learning Engineer, Inference - USA
Staff / Senior Staff Machine Learning Engineer, Inference - USA

BITKRAFT Ventures • Mountain View (CA)

On-site
USD 270,000 - 430,000
Relocation assistance
Equity
Benefits
Staff / Senior Staff Machine Learning Engineer, Inference - Switzerland
Staff / Senior Staff Machine Learning Engineer, Inference - Switzerland

Inworld AI • United States

Remote
USD 172,000 - 270,000
solutions architect for AI inference
solutions architect for AI inference

Baseten • United States

Remote
USD 120,000 - 180,000
Конкурентная компенсация
Значимая доля в компании
Медицинская страховка
+4