Member Of Technical Staff (AI)

TL;DR

Member Of Technical Staff (AI): Driving the entire alignment stack including instruction tuning, RLHF, and RLAIF to push model performance with an accent on factual accuracy and robust instruction following. Focus on designing next-generation reward models, optimizing large-scale RL pipelines, and curating high-quality training data to solve complex reasoning gaps.

Location: On-site in San Francisco, London, or New York.

Company

hirify.global is an AI startup developing open-weight foundational models to make superintelligence accessible to all.

What you will do

• Lead end-to-end alignment research covering instruction tuning, RLHF, and RLAIF.
• Design next-generation reward models and optimization objectives to improve human preference performance.
• Develop synthetic data pipelines to address reasoning and behavioral limitations.
• Optimize large-scale RL pipelines for stability and computational efficiency.
• Collaborate with pre-training and evaluation teams to build tight feedback loops for model iterations.

Requirements

• Graduate degree (MS or PhD) in Computer Science, Machine Learning, or related field.
• Deep technical command of alignment methodologies such as PPO, DPO, and rejection sampling.
• Proven ability to scale alignment techniques to large-scale models.
• Strong engineering proficiency in complex ML codebases and distributed systems.
• Experience owning ambitious research or engineering agendas with measurable model performance gains.

Culture & Benefits

• Top-tier salary and equity package.
• Comprehensive health, dental, vision, and disability insurance.
• Fully paid parental leave for all new parents with family planning financial support.
• Daily lunch and dinner provided at the office.
• Relocation support and regular team off-sites and celebrations.