RL AI Research Scientist

About the role

Design and implement novel RL algorithms for training AI agents on complex, multi-step enterprise workflows
Develop and refine reward modeling, context selection, and policy optimization techniques that improve agent accuracy over extended task horizons
Run large-scale experiments, analyze results rigorously, and translate research findings into production-ready components
Collaborate closely with infrastructure engineers to ensure research prototypes scale efficiently on both cloud and on-device hardware
Contribute to the company’s intellectual property through publications, patents, and open-source contributions
Stay current with the latest advances in RL, LLM fine-tuning, and AI agent architectures, and propose new research directions

Responsibilities

• Design and implement novel RL algorithms for training AI agents on complex, multi-step enterprise workflows
• Develop and refine reward modeling, context selection, and policy optimization techniques that improve agent accuracy over extended task horizons
• Run large-scale experiments, analyze results rigorously, and translate research findings into production-ready components
• Collaborate closely with infrastructure engineers to ensure research prototypes scale efficiently on both cloud and on-device hardware
• Contribute to the company’s intellectual property through publications, patents, and open-source contributions
• Stay current with the latest advances in RL, LLM fine-tuning, and AI agent architectures, and propose new research directions

Requirements

• PhD (or equivalent research experience) in Reinforcement Learning, Machine Learning, or a closely related field
• Strong publication record at top venues (NeurIPS, ICML, ICLR, AAAI, or equivalent)
• Deep expertise in RL fundamentals: policy gradient methods, value-based methods, model-based RL, multi-agent RL, or RLHF/RLAIF
• Proficiency in Python and at least one deep learning framework (PyTorch strongly preferred)
• Experience training and fine-tuning large language models is a significant plus
• Demonstrated ability to take research from prototype to production

Qualifications

• Experience with on-device or edge inference optimization (quantization, distillation, MoE architectures)
• Familiarity with enterprise software deployment, compliance, or regulated industries
• Track record of open-source contributions in RL or LLM ecosystems
• Experience with distributed training at scale (FSDP, DeepSpeed, Megatron)

Skills

• Strong publication record at top venues (NeurIPS, ICML, ICLR, AAAI, or equivalent)
• Deep expertise in RL fundamentals: policy gradient methods, value-based methods, model-based RL, multi-agent RL, or RLHF/RLAIF
• Proficiency in Python and at least one deep learning framework (PyTorch strongly preferred)
• Experience training and fine-tuning large language models is a significant plus
• Experience with on-device or edge inference optimization (quantization, distillation, MoE architectures)
• Familiarity with enterprise software deployment, compliance, or regulated industries
• Track record of open-source contributions in RL or LLM ecosystems
• Experience with distributed training at scale (FSDP, DeepSpeed, Megatron)

Benefits

• Direct impact on the product
• Access to cutting-edge research
• The opportunity to shape the future of enterprise AI from the ground up

Pay

Commensurate with experience

Schedule

Full-time