Applied AI Researcher, Post-Training
Applied AI Researcher, Post-Training
Applied AI Researcher, Post-Training
Distyl
Distyl AI is seeking an Applied AI Researcher for their Post-Training team, focusing on adapting foundation models for real-world applications in enterprise settings. The role involves innovative research to align AI models with human and system objectives, contributing to impactful AI deployments across various industries.
Qualification
- Deep understanding of post-training techniques including supervised fine-tuning and preference optimization.
- Experience adapting frontier models to specialized domains or behaviors.
- Expertise in building intelligent systems using models rather than just training them.
- Familiarity with techniques like LoRA/PEFT and instruction-tuning pipelines.
- Strong research track record in AI and machine learning.
Responsibility
- Adapt foundation models to meet real-world performance and alignment requirements.
- Develop and evaluate techniques such as supervised fine-tuning, preference optimization, 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 and effectively across industries.
