Research Engineer - Posttraining

Remote Jobs; Menlo Park (CA); On-site; USD 120,000 - 160,000; Full time

Job summary

A leading scientific research organization in Menlo Park is seeking a candidate proficient in creating and scaling reinforcement learning environments. You'll work with cutting-edge AI technology, operate advanced equipment, and contribute to significant scientific discoveries. Ideal candidates will have experience collaborating with experts and developing evaluations for large language models. Join a dynamic team dedicated to fostering innovation in the field.

Qualifications

• Experience in creating and scaling RL environments for large language models (LLMs).
• Proven ability to develop high‑quality evaluations for frontier models.
• Experience collaborating with domain experts to define evaluation criteria and tools.

Responsibilities

• Post‑train frontier models to autonomously execute various components of the scientific discovery pipeline.
• Generate hypotheses and design experiments to be conducted in a laboratory setting.
• Operate advanced scientific equipment as part of the research process.

Skills

Experience in creating and scaling RL environments

Ability to develop high‑quality evaluations for frontier models

Collaboration with domain experts

Crafting training datasets and reward functions

Training frontier LLMs using reinforcement learning techniques

Job description

Employer Industry: Scientific Research and Development

Why consider this job opportunity

• Opportunity to work with cutting‑edge AI and physical sciences technology
• Collaborate with leading experts in the field
• Engage in meaningful scientific discovery and innovation
• Work in a dynamic and rapidly growing organization
• Chance to influence the automation of scientific processes

What to Expect (Job Responsibilities)

• Post‑train frontier models to autonomously execute various components of the scientific discovery pipeline
• Generate hypotheses and design experiments to be conducted in a laboratory setting
• Operate advanced scientific equipment as part of the research process
• Create high‑quality evaluation and training tasks for model assessment
• Scale up reinforcement learning (RL) environments and run large‑scale RL experiments

What is Required (Qualifications)

• Experience in creating and scaling RL environments for large language models (LLMs)
• Proven ability to develop high‑quality evaluations for frontier models
• Experience collaborating with domain experts to define evaluation criteria and tools
• Proficient in crafting training datasets and reward functions, utilizing LLMs and/or human trainers
• Experience in training frontier LLMs using reinforcement learning techniques

How to Stand Out (Preferred Qualifications)

• Strong understanding of AI methodologies and scientific research processes
• Familiarity with sophisticated scientific equipment and experimental design
• Previous experience in a fast‑paced, innovative research environment

We prioritize candidate privacy and champion equal‑opportunity employment. Central to our mission is our partnership with companies that share this commitment. We aim to foster a fair, transparent, and secure hiring environment for all. If you encounter any employer not adhering to these principles, please bring it to our attention immediately. We are not the EOR (Employer of Record) for this position. Our role in this specific opportunity is to connect outstanding candidates with a top‑tier employer.