Research Engineer, Post-Training

Storm3; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Medical Insurance

Dental Insurance

Vision Insurance

Competitive salary

Collaborative team of researchers

Job summary

Fundamental AI Research Institute in San Francisco is seeking researchers experienced in LLM post-training, agentic infrastructure, RL environments, and evaluation harnesses to accelerate flagship AI research. Responsibilities include building and scaling post-training platforms and RL infra, developing benchmarks, contributing to deployment of large-scale models, and publishing results at top conferences.

Join a fast-growing team with ample GPU resources and a collaborative culture, offering a

Qualifications

• Strong publication record in top conferences, or contribution to leading AI models, datasets and benchmarks.
• 2+ years industry experience, focused on RL, Evals, Reasoning, Agents or AI infra
• Comfortable navigating ambiguity and impacting research direction

Responsibilities

• Build and scale the post-training platform and RL infrastructure, including developing agentic and evaluation harnesses
• Develop benchmarks and evaluations for reasoning and agentic capabilities
• Contribute towards deployment and productionization of large-scale models
• Publish breakthrough findings and reports in top conferences

Skills

RL

Evaluations

Reasoning

Agents

AI infra

Publications

Job description

Fundamental AI Research Institute

Come join one of the only research institutions globally with resources to compete with top AI companies => 10s of 1000s of GPUs and Tier1 talent.

This lab is a playground for state-of-the-art research in LLMs, Reinforcement Learning and Agentic AI.

Hiring for those experienced in LLM Post-Training / Agentic infrastructure, building RL environments, evaluation harnesses and post-training platforms to accelerate research.

Responsibilities:

• Build and scale the post-training platform and RL infrastructure, including developing agentic and evaluation harnesses
• Develop benchmarks and evaluations for reasoning and agentic capabilities
• Contribute towards deployment and productionization of large-scale models
• Publish breakthrough findings and reports in top conferences

Requirements:

• Strong publication record in top conferences, or contribution to leading AI models, datasets and benchmarks
• 2+ years industry experience, focused on RL, Evals, Reasoning, Agents or AI infra
• Comfortable navigating ambiguity and impacting research direction

Why apply:

• Opportunity to join a fast-growing core team that are already pushing AI breakthroughs
• Highly competitive salary package
• Work alongside ambitious and bright superstars from tech and academia
• Medical, Dental and Vision Insurance