Member of Technical Staff, Post-Training (AI)

Location: San Jose, United States

Salary: $180,000–$450,000 annually

Company

hirify.global is an artificial intelligence company developing personalized, proactive, multimodal intelligence and next-generation hardware as a unified interface between humans and machines.

What you will do

• Design and implement primarily reinforcement-learning-based post-training strategies for coding agents with multi-step reasoning, tool use, and long-horizon task completion.
• Build and scale code execution sandboxes, computer-use environments, tool-calling harnesses, and verifiable reward systems for agentic reinforcement learning.
• Develop outcome-based, execution-based, and process-based reward modeling pipelines.
• Scale synthetic data generation and trajectory distillation pipelines to improve reinforcement learning sample efficiency.
• Run ablation studies and diagnose interactions between algorithms, data mixtures, reward shaping, and scale.
• Build evaluations for code correctness, execution success, and multi-step tool use while collaborating with mid-training, infrastructure, and product teams.

Requirements

• Strong machine learning background with hands-on experience training or fine-tuning large language, multimodal, or equivalent models.
• Deep understanding of reinforcement learning, including policy optimization, reward design, exploration, and environment design.
• Experience with simulation or execution environments such as code interpreters, sandboxes, game environments, or robotics simulators.
• Ability to design rigorous experiments, diagnose training failures, and identify scaling bottlenecks.
• Proficiency in Python and PyTorch, with comfort working across research and systems code.
• Ability to work in a fast-moving, research-focused environment where approaches may be uncertain initially.

Nice to have

• Experience applying RL algorithms such as RLHF, DPO, GRPO, or PPO to language or code.
• Familiarity with coding-agent benchmarks including SWE-bench, HumanEval, or LiveCodeBench.
• Experience with reward modeling, trajectory-based training, imitation learning, or data distillation.
• Experience with computer-use agents, GUI agents, or tool-using language models.
• Experience training or scaling models with 10B+ parameters, or contributions to open-source ML projects and research publications.

Culture & Benefits

• Research-forward environment focused on emerging agentic AI capabilities.
• Opportunity to work at the intersection of reinforcement learning, simulation, and large-scale model training.
• Full-time employment with an annual US base salary range of $180,000–$450,000.
• Total compensation may include additional components and benefits depending on the role.