Member of Technical Staff, Model Training (post-training research) (AI)

Location: Remote, US

Base salary: $200,000–$320,000 annually; equity and performance-based bonuses may also apply.

Company

hirify.global develops and operates large-scale AI models and provides a remote-first workforce environment.

What you will do

• Research, implement, and scale supervised fine-tuning, reinforcement learning, and on-policy distillation methods for large language and multimodal models.
• Investigate learning objectives, optimization dynamics, exploration, credit assignment, and training recipes to improve stability, sample efficiency, and capability acquisition.
• Design methods using expert demonstrations, human preferences, corrections, and model-generated trajectories.
• Research generators, reward models, and graders to improve model performance and training-signal quality.
• Design experiments, ablation studies, and evaluation frameworks for generalization, reasoning, and realistic downstream tasks.
• Own research initiatives end-to-end, from hypothesis formulation and algorithm implementation through large-scale experiments and validation.

Requirements

• Strong foundations in machine learning, deep learning, optimization, and modern model training techniques.
• Hands-on experience training, fine-tuning, or post-training large-scale language or multimodal models.
• Deep technical expertise in one or more of reinforcement learning, model distillation, reward modeling, data selection, or learning dynamics.
• Strong proficiency in Python and PyTorch, including implementing, debugging, and optimizing complex training pipelines.
• Experience designing controlled experiments, interpreting model behavior, and translating empirical findings into research directions.
• Ability to independently navigate ambiguous research problems, formulate hypotheses, and iterate based on experimental evidence.
• Strong analytical thinking, research orientation, reproducibility, scientific rigor, and focus on measurable improvements.

Nice to have

• Experience with RLHF, RLAIF, preference optimization, or reinforcement learning for reasoning and agentic tasks.
• Familiarity with distributed training, large-scale experimentation, and GPU-based model optimization.
• Experience developing reward models, verifiers, graders, or automated evaluation systems.
• Research contributions to post-training, reinforcement learning, or related areas through publications, open-source projects, or production systems.
• Experience with synthetic data generation, curriculum learning, or iterative self-improvement techniques.

Culture & Benefits

• Full-time position within a remote-first workforce.
• Health-insurance premium reimbursement of up to 100%.
• Paid time off and a 401(k) plan with company match.
• Equity compensation and potential performance-based bonuses.
• AI tools assist with candidate screening and assessment while supporting human decision-making.