T

Research Scientist, RL Post-Training

trimah technologies llc • United State
Visa Sponsorship
Apply Now

Join a days-old AI agents lab as a Research Scientist focused on RL post-training, working on long-horizon autonomous agents from research through deployment. Build complete systems including environments, training-data pipelines, and eval harnesses in a high-ownership, fully in-office role in San Francisco. Requires exceptional ML research and engineering ability with deep experience in RL, LLM post-training, agents, or related areas.

Key Highlights
4 openings for Research Scientists specializing in RL post-training at a new AI agents lab
Founders from Tesla AI, Anthropic, DeepMind, NVIDIA Research, and Jane Street
Salary range $250k–$500k base plus 1–5% equity, fully in-office in San Francisco
Key Responsibilities
Conduct ML research and engineering focused on RL post-training for autonomous agents
Build complete systems including environments, training-data pipelines, and eval harnesses
Own long-horizon agent projects end to end, from training through deployment
Technical Skills Required
Reinforcement Learning Machine Learning LLM Post-Training
Benefits & Perks
Equity compensation (1–5%)
Visa sponsorship available
Paid research work trial (2–3 days) with expenses covered
Nice to Have
Work directly on RL post-training, agents, long-horizon systems, computer-use, memory/context, evals, or human-agent interaction
Strong publication, open-source, or benchmark record in relevant areas
Environments, training-data-pipeline, or eval-harness building experience
Olympiad (IOI/IMO), quant, or world-class competitive achievement background

Job Description

Hiring: Research Scientist, RL post-training 4 seats · San Francisco · $250k to $500k base + 1 to 5% equity

The company: a days-old AI agents lab, founders from Tesla AI, Anthropic, DeepMind, NVIDIA Research and Jane Street.

Requirements

Exceptional ML research and engineering ability

Deep experience in one or more of: LLM post-training, RL, agents, reasoning, long-horizon systems, memory/context, computer use, evals, or human-agent interaction

Strong experimental judgment; builds complete systems, not isolated prototypes

Moves fluidly between research ideas, large-scale experimentation, and production systems

Want the full job description? Read the complete details on LinkedIn, the original posting.
Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.

See Jaabz jobs first on Google 1 tap · free · in AI Overviews Jaabz is on your Google Manage Preferred Sources

Similar Jobs

Explore other opportunities that match your interests

Senior Full Stack Software Engineer - Cyber Engineering

Programming
•
45m ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

Deloitte

United State
Visa Sponsorship Relocation Remote
Job Type Full-time
Experience Level Not Applicable

Deloitte

United State

Manager, Technology Risk & Compliance - Global Audit & Assurance Digital Products

Programming
•
1h ago

Premium Job

Sign up is free! Login or Sign up to view full details.

•••••• •••••• ••••••
Job Type ••••••
Experience Level ••••••

Deloitte

United State

Subscribe our newsletter

New Things Will Always Update Regularly