Назад
Company hidden
2 дня назад

Research Engineer (Post-Training)

160 000 - 240 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
senior
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
Research Engineer (Post-Training) (Enterprise AI): Developing and optimizing post-training methods, scalable training pipelines, and evaluation systems for large generative models with an accent on supervised fine-tuning, reinforcement learning, preference optimization, and GPU efficiency. Focus on designing rigorous experiments, analyzing training dynamics, investigating model failures, and translating research ideas into measurable model improvements.

Location: Mountain View, CA — Downtown HQ; on-site five days per week

Salary: $160K–$240K annually, plus equity and performance bonus

Company

hirify.global builds an efficiency and intelligence layer for enterprise AI across data processing, large tabular models, and stateful AI agents, helping customers operate AI systems with less data, compute, and infrastructure overhead while retaining control of enterprise data and intelligence.

What you will do

  • Develop and optimize post-training methods including supervised fine-tuning, reinforcement learning, and preference optimization.
  • Design training objectives, reward functions, synthetic data strategies, and model adaptation techniques.
  • Build scalable training, rollout, and evaluation pipelines for large generative models.
  • Design rigorous experiments, run ablations, analyze training dynamics, and investigate model failures.
  • Optimize GPU-based training systems for performance, efficiency, reproducibility, and reliability.
  • Collaborate with research scientists and the research team to implement novel ideas and improve model capabilities.

Requirements

  • PhD in Computer Science, Machine Learning, Applied Mathematics, Statistics, or a closely related field, completed or nearing completion, or equivalent industry research and engineering experience.
  • Hands-on experience with model post-training, including SFT, RLHF, GRPO, PPO, DPO, or related techniques.
  • Strong foundations in deep learning, reinforcement learning, optimization, and modern generative models.
  • Strong Python programming skills and deep proficiency with PyTorch or JAX.
  • Experience implementing, debugging, and optimizing GPU-based model-training pipelines.
  • Strong experimental judgment in model evaluation, ablation studies, training diagnostics, and performance analysis.
  • Ability to independently translate research ideas into efficient implementations, investigate unexpected model behavior, and iterate toward measurable improvements.

Nice to have

  • Academic or industry ML research experience with original contributions to model architectures, training methods, or optimization algorithms.
  • Publications at leading machine learning conferences such as NeurIPS, ICML, or ICLR.
  • Experience with distributed training, large-scale reinforcement learning, or verl, TRL, DeepSpeed, or Ray.
  • Experience with reward modeling, synthetic training data, agentic reinforcement learning, or automated evaluation systems.
  • Experience developing or post-training foundation models for structured data, specialized domains, or complex reasoning tasks.

Culture & Benefits

  • Full-time, on-site work at the Mountain View office five days per week.
  • Meaningful equity and performance bonus for top performers.
  • 401(k) with company match and comprehensive health coverage.
  • Unlimited paid time off and daily catered meals at the Mountain View office.
  • Support for research, publication, and conference 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 →