Research Scientist (Reinforcement Learning)

Location: On-site in San Francisco, California, United States

Salary: $200,000–$335,000 annual base salary, plus equity and benefits

Company

hirify.global builds continual-learning infrastructure that enables enterprises to train and deploy agent workforces on proprietary data and institutional expertise.

What you will do

• Design, implement, and optimize reinforcement learning training and inference pipelines across large GPU clusters.
• Build tooling and observability for inspecting, profiling, and debugging training runs.
• Develop reliable systems that account for low-precision numerics and distributed-training edge cases.
• Partner with researchers to bring frontier post-training capabilities into production deployments.

Requirements

• Experience programming with and managing training jobs on large-scale GPU systems.
• Curiosity and ability to understand all levels of the training stack.
• Strong focus on fast implementation, reliability, and efficiency.
• Familiarity with open-weights model architectures and inference.
• Background in reinforcement learning or integrating inference with RL training loops.
• Ability to work on-site from the San Francisco office.

Nice to have

• Experience with distributed training frameworks such as PyTorch, JAX, or DeepSpeed.
• Background in high-performance computing or large-scale clusters.
• Open-source contributions to ML infrastructure.
• Published projects, open-source contributions, or side projects demonstrating technical creativity.

Culture & Benefits

• Competitive compensation, meaningful equity, and retirement plans.
• 100% employer-paid health insurance.
• Unlimited paid time off and paid parental leave.
• Daily lunches and dinners.
• Transportation and relocation support.
• Visa sponsorship is available.