Distyl

Applied AI Researcher, Post-Training

San Francisco, Remote. Posted 13 months ago

The role

Researchers on the Post-Training team adapt foundation models to real-world performance and alignment requirements. They develop and evaluate techniques like supervised fine-tuning and preference optimization to bridge raw model capability with trustworthy system behavior.

What you will do

  • Adapt foundation models to real-world performance and alignment requirements
  • Develop and evaluate techniques such as supervised fine-tuning, preference optimization (DPO, RLHF, RLAIF), and continual adaptation
  • Investigate new methods for aligning large models with human and system-level objectives
  • Explore trade-offs between generalization and specialization, data efficiency and robustness, capability and controllability
  • Inform how Distyl leverages foundation models safely, effectively, and at scale across industries
  • Build prototypes of ideas and perform experiments to prove effectiveness

Required qualifications

  • Familiarity with supervised fine-tuning, preference optimization (RLHF/DPO), LoRA/PEFT, and instruction-tuning pipelines
  • Experience tuning or adapting LLMs/SLMs to specialized domains or behaviors through data curation, reward modeling, or continual pretraining
  • Expertise in compound AI systems, agentic collaboration, and associated techniques (ensembling, ReAct, graph-of-thoughts, etc.)
  • Proven track record of research results
  • Uses tools like ChatGPT, Cursor, and Perplexity to accelerate workflow
  • Strong programming and data analysis skills
  • Biases towards showing vs telling

Benefits

  • 100% coverage of medical, dental, and vision insurance for employee and dependents
  • Flexible time off
  • Retirement and financial planning benefits, including access to pre-tax HSA, FSA, and commuter accounts, 401(k), and financial coaching resources
  • Comprehensive wellness benefits, including physical fitness, mental well-being, and fertility and family-building benefits through Carrot
  • Complimentary in-office lunches and snacks provided
  • Access to state-of-the-art AI models, generous usage of modern AI tools, and real-world business problems
  • Ownership of high-impact projects across top enterprises
  • A mission-driven, fast-moving culture that values curiosity, pragmatism, and excellence

About the company

Distyl is an applied AI technology company partnering with the world’s most ambitious institutions to rearchitect critical operations for the frontier of AI. They research and deploy technologies that power AI-native operations.