Research Scientist

Research Scientist / Machine Learning Scientist

Location:

SF Bay Area/Hybrid / Remote

Type:

Full-Time

About the Role:

The Clientis seeking a variety of Machine Learning Scientist to help advance how we evaluate and understand AI models. You’ll help design and analyze experiments that uncover what makes models useful, trustworthy and capable through human preference signals. Your work will contribute to the scientific foundations of understanding AI at scale.

This role is deeply interdisciplinary. You’ll work closely with engineers, product teams, marketing and the broader research community to develop new methods for comparing models, analyzing preference data, and disentangling performance factors like style, reasoning, and robustness. Your work will inform both the public leader board and the tools we provide to model developers.

If you’re excited by open-ended questions, rigorous evaluation, and research that’s grounded in real-world impact, you’ll find a meaningful home here. We’re looking for:

• Hands-on experience training large-scale models, including reward models, preference models, and fine-tuning LLMs with methods like RLHF, DPO, and contrastive learning.

• Strong foundation in ML and statistics, with a track record of designing novel training objectives, evaluation schemes, or statistical frameworks to improve model reliability and alignment.

• Fluent in the full experimental stack, from dataset design and large-batch training to rigorous evaluation and ablation, with an eye for what scales to production.

• Deeply collaborative mindset, working closely with engineers to product ionize research insights and iterating with product teams to align modeling goals with user needs.

Responsibilities:

• Design and conduct experiments to evaluate AI model behavior across reasoning, style, robustness, and user preference dimensions

• Develop new metrics, methodologies, and evaluation protocols that go beyond traditional benchmarks

• Analyze large-scale human voting and interaction data to uncover insights into model performance and user preferences

• Collaborate with engineers to implement and scale research findings into production systems

• Prototype and test research ideas rapidly, balancing rigor with iteration speed

• Author internal reports and external publications that contribute to the broader ML research community

• Partner with model providers to shape evaluation questions and support responsible model testing

• Contribute to the scientific integrity and transparency of theThe Clientleaderboard and tools

Who isThe Client?

Created by researchers from

UC Berkeley’s Sky Lab,The Clientis an open platform where everyone can easily access, explore and interact with the world’s leading AI models. By comparing them side by side and casting votes for the better response, the community helps shape a public leader board, making AI progress more transparent, and grounded in real-world usage.

Why Join Us?

Trusted by organizations like Google,OpenAI,Meta, xAI, and more,The Clientis rapidly becoming essential infrastructure for transparent, human-centered AI evaluation h over one million monthly users and growing developer adoption, our impact is helping guide the next generation of safe, aligned AI systems—grounded in open access and collective feedback.

Our work is regularly referenced by industry leaders pushing the frontier of safe and reliable AI.Sundar Pichai,Jeff Dean,Elon Musk, andSam Altman.

• High Impact:
Your work will be used daily by the world’s most advanced AI labs.

• Global Reach:
Develop data infrastructure powering millions of real-world evaluations, influencing AI reliability across industries at the top-tier

• Exceptional Team:
We are a small team of top talent from Google, Deep Mind, Discord,Vercel,UC Berkeley, and Stanford.

Requirements:

• PhD or equivalent research experience in Machine Learning, Natural Language Processing, Statistics, or a related field

• Strong understanding of LLMs and modern deep learning architectures (e.g., Transformers, diffusion models, reinforcement learning with human feedback)
Proficiency in Python and ML research libraries such as PyTorch, JAX, or Tensor Flow

• Demonstrated…