Member of Technical Staff (AI)

Location: On-site in San Francisco, United States

Company

hirify.global is building interactive world models and simulation infrastructure for robotics, embodied AI, and intelligent digital environments.

What you will do

• Build reinforcement learning and post-training pipelines for multimodal, vision-language, and code-generating agents.
• Develop infrastructure for supervised fine-tuning, preference optimization, reward modeling, and reinforcement learning.
• Create systems to collect, filter, replay, and learn from agent trajectories.
• Design rewards, verifiers, and evaluations for long-horizon agent tasks.
• Improve agents’ planning, code generation and execution, tool use, error recovery, and complex workflow completion.
• Scale distributed training and high-throughput rollout generation across multi-GPU environments while improving reliability, observability, reproducibility, and cost efficiency.

Requirements

• Real-world experience training large language, vision-language, multimodal, or code models.
• Strong experience with reinforcement learning, post-training, or large-scale fine-tuning.
• Experience building distributed training or high-throughput inference systems.
• Familiarity with supervised fine-tuning, preference optimization, reward modeling, and agentic reinforcement learning.
• Strong Python skills and experience with PyTorch, JAX, or similar frameworks.
• Ability to work across data, models, environments, rewards, evaluations, and infrastructure, with strong research judgment.

Nice to have

• Experience at a frontier AI lab or with large-scale training systems.
• Experience with code-model post-training, autonomous coding agents, multimodal models, robotics, simulation, or embodied AI.
• Experience designing verifiable rewards or outcome-based training systems.
• Experience scaling reinforcement learning workloads across large GPU clusters.

Culture & Benefits

• Work as part of an engineering and research team focused on AI infrastructure for interactive digital and physical worlds.
• Collaborate closely with the research team on agent training and model improvement.
• Help shape the long-term strategy for agent, robotics, and embodied-model training.
• Full-time, on-site work in San Francisco.