Member of Technical Staff, Post-Training (AI)

Location: Palo Alto, United States; onsite

Company

hirify.global Intelligence is a frontier AI lab building self-improving systems for chip design and connecting AI models with the hardware that runs them.

What you will do

• Design and iterate SFT and RL recipes for large-scale models, focusing on compute efficiency and stable RL improvement.
• Build and scale synthetic data pipelines covering generation, quality filtering, and coverage metrics.
• Create long-horizon synthetic environments and task curricula for agentic coding and reasoning.
• Stabilize RL at scale and build evaluations that track agentic capability, detect regressions, and guide recipe decisions.
• Own experiments end to end on large GPU clusters, including design, launch, debugging, and analysis.
• Partner with teammates to improve post-training efficiency across training and serving platforms.

Requirements

• Degree in CS, EE, mathematics, or a related field, or equivalent practical experience.
• Hands-on post-training experience with SFT, RL, synthetic data, and environments at a frontier AI lab or equivalent.
• Deep understanding of transformer internals and distributed training.
• A shipped post-training run, model release, or research outcome that improved a benchmark or product.

Nice to have

• Research track record in RL, NLP, or machine learning, including publications at NeurIPS, ICML, ICLR, or COLM.
• Experience building RL environments for complex frontier coding and agentic benchmarks.
• Experience shipping synthetic data generation and filtering at scale.
• Experience shipping RL infrastructure such as asynchronous rollouts and inference engines including vLLM or SGLang.
• Experience navigating ambiguity and making design decisions across the stack.
• Interest in applying LLMs to hardware and chip design; prior experience is not required.

Culture & Benefits

• Fast-paced frontier AI research environment where each hire directly shapes the work.
• Work alongside researchers and engineers with backgrounds at Anthropic, Google DeepMind, Stanford, MIT, Apple, and Google.
• Contribute to self-improving AI systems and research at the intersection of models and chip design.