Researcher (Reinforcement Learning)

TL;DR

Researcher (Reinforcement Learning): Developing novel reinforcement learning techniques leveraging synthetic data, environments, and feedback to train and evaluate frontier AI models with an accent on self-play, simulators, and other synthetic evaluations. Focus on designing experiments, analyzing learning dynamics, and translating research insights into production training approaches.

Location: Hybrid (San Francisco, CA) with 3 days in office per week. Relocation assistance to San Francisco, CA is offered.

Salary: $310,000–$460,000 + Offers Equity

Company

hirify.global is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.

What you will do

• Research and develop reinforcement learning algorithms.
• Design and run experiments to study training dynamics and model behavior at scale.
• Collaborate with engineers and researchers to integrate successful approaches into model training pipelines.

Requirements

• Strong background in reinforcement learning, machine learning research, or related fields.
• Strong engineering and statistical analysis skills.
• Enjoys exploring new problem spaces where data, objectives, and evaluation are imperfect or evolving.
• Motivated by seeing research ideas influence real-world AI systems.

Culture & Benefits

• Work on open-ended problems with a focus on fast iteration.
• Directly shape how frontier models are trained.
• Committed to providing reasonable accommodations to applicants with disabilities.
• An equal opportunity employer, promoting diversity and inclusion.