Applied AI Researcher, Post-Training
$150k - $250k • San Francisco • FullTime
Posted 1y ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
Applied AI Engineer
About the job
Distyl AI is seeking creative researchers to join our Post-Training team, focusing on adapting foundation models to meet real-world performance and alignment requirements for enterprise AI. This role involves developing and evaluating techniques to align models with business systems, bridging raw model capability with trustworthy, contextually aligned behavior. Researchers will investigate new methods for aligning large models with human and system-level objectives, exploring trade-offs in generalization, data efficiency, and controllability to ensure safe, effective, and scalable AI deployment across industries. The ideal candidate is driven by a desire to redefine how software is used through AI, rather than just incremental improvements.
Responsibilities
- Develop and evaluate techniques for adapting foundation models, such as supervised fine-tuning, preference optimization (DPO, RLHF, RLAIF), and continual adaptation.
- Align models with Distyl's enterprise systems to achieve trustworthy and contextually aligned behavior.
- Investigate new methods for aligning large models with human and system-level objectives.
- Explore trade-offs between generalization and specialization, data efficiency and robustness, and capability and controllability.
- Inform how Distyl leverages foundation models safely, effectively, and at scale across industries.
- Build intelligent systems using models, focusing on compound AI systems, agentic collaboration, and associated techniques like ensembling, ReAct, and graph-of-thoughts.
- Prototype ideas and perform experiments to demonstrate effectiveness to stakeholders.
Requirements
- Deep understanding of post-training techniques including supervised fine-tuning, preference optimization (RLHF/DPO), LoRA/PEFT, and instruction-tuning pipelines.
- Experience adapting frontier models (LLMs/SLMs) to specialized domains or behaviors through data curation, reward modeling, or continual pretraining.
- Experience building intelligent systems using models, with expertise in compound AI systems, agentic collaboration, and techniques like ensembling, ReAct, and graph-of-thoughts.
- Proven track record of research results (publications, public work, etc.).
- Daily use of AI tools such as ChatGPT, Cursor, and Perplexity.
- Strong programming and data analysis skills for prototyping and experimentation.
- Bias towards demonstrating practical AI applications over theoretical concepts.
Benefits
- Base salary range of $150K – $250K.
- Meaningful equity.
- Comprehensive benefits package.
- 100% coverage of medical, dental, and vision insurance for employee and dependents.
- Flexible time off.
- Retirement and financial planning benefits (HSA, FSA, 401(k), financial coaching).
- Comprehensive wellness benefits (physical fitness, mental well-being, fertility and family-building).
- Complimentary in-office lunches and snacks.
- Access to state-of-the-art AI models and generous usage of modern AI tools.
- Ownership of high-impact projects across top enterprises.