Research Scientist - Agents (Post Training)

• Propose, prototype, and scale algorithms/systems to support agentic learning
• Develop new paradigms for agentic behavior that go beyond current practices
• Contribute to technical reports, research publications, and open-source software
• Collaborate with other teams to produce state-of-the-art foundation models

• BS, MS, or PhD degree (or equivalent experience) in Computer Science, Machine Learning, or related fields

Professional Experience

• Expertise in one or more of PyTorch, Ray, Triton, CUDA C++
• Strong knowledge of literature on RL, LLM reasoning, and tool use
• Experience in training or using LLM agents for SWE tasks
• Deep understanding of reinforcement learning principles
• Experience implementing distributed learning algorithms
• Contributions to published research and/or open-source ML software

We are a dedicated research lab for building, understanding, using, and risk-managing foundation models. Our mandate is to advance research, nurture the next generation of AI builders, and drive transformative contributions to a knowledge-driven economy.

As part of our team, you’ll have the opportunity to work on the core of cutting-edge foundation model training, alongside world-class researchers, data scientists, and engineers, tackling the most fundamental and impactful challenges in AI development. You will participate in the development of groundbreaking AI solutions that have the potential to reshape entire industries. Strategic and innovative problem-solving skills will be instrumental in establishing MBZUAI as a global hub for high-performance computing in deep learning, driving impactful discoveries that inspire the next generation of AI pioneers.

Position Summary

As a member of the Agents team, you will tackle research and engineering challenges to train advanced agentic language models that are adept at using reasoning and tool use to complete tasks on a computer. These challenges range from building high-quality training datasets and robust evaluations to innovative reinforcement learning infrastructure, algorithms and environments. The team aims to recruit candidates across the research-engineering spectrum, from algorithmic and empirical research to large-scale systems and optimization, reflecting the breadth of interesting problems we aim to solve.

We value depth in any subset of these areas; there is no single “right” background.

• 2 years of experience working in one of the following or related areas: LLM training/fine-tuning, evaluations, reinforcement learning, LLM inference, distributed machine learning systems
• Python and PyTorch development experience
• Experience in using LLM agents for your personal or professional use
• Experience in designing and implementing algorithms from scratch (for algorithms focus)
• Experience in dataset curation and generation (for data focus)
• Experience in building or contributing to training/serving infrastructure (for systems focus)
• Experience in designing and deep diving into evaluations (for evals focus)

Compensation

$150,000 – $450,000/year + discretionary performance bonus + benefits

The posted salary range represents the company’s good faith estimate of the base compensation for this position upon hire. The actual base compensation offered may vary within this range depending on individual qualifications, including but not limited to relevant skills, experience, education, certifications, and specific business needs. In addition to base salary, total compensation includes an annual discretionary performance bonus and comprehensive benefits.

Benefits Include

• Comprehensive medical, dental, and vision benefits
• Bonus
• 401K Plan
• Generous paid time off, sick leave and holidays
• Paid Parental Leave
• Employee Assistance Program
• Life insurance and disability

This position is eligible for visa sponsorship.