ml engineer for AI companions

Joi AI

United States

Remote

USD 150,000 - 210,000

Full time

14 days+

Get a reply from this employer

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

Get past ATS filters

Benefits offered by this job

Ежегодный отпуск 28 дней
Ежегодные wellness-дни
Referral бонус до $5000
Скидки на английский
Медицинские расходы до $1000
Оборудование для дома

Job summary

Joi AI ищет опытного инженера по ML для ускорения и масштабирования инференса LLM, обучения и донастройки моделей для ассистентов и генеративных задач. Участие в развитии инференса на многопроцессорных кластерах и лидерство в технических обсуждениях.

Требуется продвинутый уровень английского или русского языка и опыт в PyTorch/Transformers. Кандидат будет работать над улучшением чат-алгоритмов и агентских хэндлов, сотрудничать с командами валидации и подготовки датасетов, а также участвовать в

Qualifications

  • Есть опыт оптимизации вывода LLM в продакшне с SGLang, vLLM или TensorRT-LLM.
  • Опыт распределенного вывода или обучения больших моделей (MoE, параллелизм).
  • Понимание KV-кеша, attention kernels, батчинг, квантование и профилирование GPU.
  • Опыт обучения и тонкой настройки LLM, включая RLHF/DPO.
  • Умение работать с PyTorch и библиотеками transformers.

Responsibilities

  • Ускорять и масштабировать вывод LLM в продакшн с использованием SGLang, KV и пр.
  • Запуск распределенного вывода для очень больших моделей на multi-GPU/многоузлах.
  • Бенчмаркить новые GPU-серверы и внедрять в прод
  • Техническое руководство NLP и CV командами, направление и решения.
  • Обучать и подбирать LLM, улучшать агентов и чат-алгоритмы.
  • Отслеживать инференс и пост-обучение; формировать ML-дорожную карту.
  • Сотрудничать с Validation/Content/Dataset командами для дизайна экспериментов.

Skills

LLM inference optimization
Distributed inference
KV cache
Attention kernels
Batching
Quantization
GPU profiling
LLM fine-tuning
PyTorch
Transformers
English or Russian

Education

CS/Math/Physics degree (MSc/PhD)

Tools

Python
Go
C#
CUDA
Triton
PyTorch
Transformers

Job description

Описание

Joi AI is a platform for AI-lationships: personalized, emotionally intelligent connections between people and AI characters. It serves emotional and intimate needs and has tens of millions of conversations. Joi Lab is its open research arm, building open-source generative models, agent architectures, and training infrastructure.

Задачи
  • Speed up and scale production LLM inference using SGLang, KV and prefix caching, batching, quantization, and speculative decoding
  • Run distributed inference for very large models across multi-GPU and multi-node setups
  • Benchmark new GPU servers and hardware, bring them into production, and adapt serving code
  • Lead NLP and CV teams technically by reviewing experiments, setting direction, and addressing wrong turns early
  • Train and fine-tune language models for AI companions and improve agent harnesses and chat algorithms
  • Track inference and post-training research and open-source work, and turn findings into the ML roadmap
  • Collaborate with validation, content, and dataset preparation teams to design experiments and measure model quality
Требования
  • Deep hands-on experience optimizing production LLM inference with SGLang, vLLM, or TensorRT-LLM
  • Experience with distributed inference or training of large models, including MoE, tensor/expert/pipeline parallelism, and multi-node GPU clusters
  • Strong understanding of KV cache, attention kernels, batching, quantization, and GPU profiling
  • Experience training and fine-tuning LLMs, including post-training such as RLHF or DPO
  • Proven technical leadership through reviews, mentoring, and technical decisions while continuing to write codeProficiency with PyTorch, transformers, and related libraries
  • Advanced English or Russian
  • Будет плюсом: experience at AI-focused startups or companies such as Character AI or OpenAI, backend engineering with Python, Go, or C#, scalable deployment systems, CUDA or Triton kernel development, a computer vision background or experience accelerating generative image or video models, multimodal LLMs, first-author papers or notable open-source contributions, a degree in CS, math, or physics (MSc or PhD)
Условия
  • 28 Days of annual leave 7 Yearly wellness days; no sick notes needed
  • Referral rewards up to $5000 50% Of training, conference, and global meetup costs covered
  • Subsidized English classes through a corporate discount
  • Up to $1,000 annually for medical fees or private insurance if not on the group plan
  • Office equipment or $1000 every three years for a home office or co-working setup
  • Gratitude bonuses redeemable for swag, massage vouchers, or team adventures
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

ml engineer for llm performance optimization
ml engineer for llm performance optimization

NDA • United States

On-site
USD 150,000 - 230,000
Leave + wellness days
Training coverage
Health stipend
+1
ML engineer LLM inference & architecture
ML engineer LLM inference & architecture

NDA • United States

On-site
USD 180,000 - 240,000
Fully remote
Home office stipend
Education support
+4
ML engineer for social discovery products
ML engineer for social discovery products

Dating Group • United States

Remote
USD 140,000 - 210,000
Vacation 28 calendar days
Wellness days 7
Referral bonuses up to $5000
+5
design director for AI companions
design director for AI companions

Joi AI • United States

Remote
USD 140,000 - 190,000
28 Days of annual leave
7 Yearly wellness days
Referral rewards up to $5000
+5
Senior ML Engineer
Senior ML Engineer

Aimlroles • United States

Remote
USD 150,000 - 230,000
Vacation 28 days
Wellness days
Bonuses up to $5,000
+4
ml engineer for LLM inference
ml engineer for LLM inference

Cast AI • United States

On-site
USD 180,000 - 270,000
Equity 10%
Annual hackathon
Learning budget
AI engineer
AI engineer

RichBrains • United States

Remote
USD 110,000 - 150,000
Remote work
Training & certifications
Team events
+2
cto for an AI-powered product
cto for an AI-powered product

NDA • United States

On-site
USD 150,000 - 210,000
21 vacation days
Public holidays
5 sick days
+2
AI LLM Engineer (Full Remote - Europe)
AI LLM Engineer (Full Remote - Europe)

EverAI Limited • United States

Remote
USD 150,000 - 230,000
Здоровье и благополучие
Оплачиваемый отпуск
Учебный бюджет
+1
AI/ML Engineer
AI/ML Engineer

Syntas • United States

Hybrid
USD 140,000 - 200,000
Fully remote work with flexible hours
Learning budget
Conference attendance budget
+4