LLM Researcher

Description

The company Robotics builds affordable humanoid robots. We're looking for hungry, talented, curious people to join our team.

Scope: Research and improve model behavior, with creative writing at the center. Fine-tune and post-train language models on text-based creative and behavioral preference data, then carry those improvements into consumer applications and robot interactions.

What you will work on

Fine-tune and post-train models for voice, character, narrative coherence, conversation, and social behavior.

Develop text-based creative and behavioral preference datasets, with clear human review and comparison criteria.

Build creative-writing benchmarks and run preference studies, ablations, and held-out evaluations to measure behavior.

Work with the VLM researcher and harness engineer to deploy improvements and study model behavior in products with real users.

Requirements

• Hands-on LLM fine-tuning and post-training, with strong Python and PyTorch or JAX and practical distributed-training experience.
• Research in model behavior, open-ended generation, or preference learning, with rigorous human evaluation and experimental design.
• Nice to have: creative-writing evaluation, long-context narrative consistency, preference learning, or relevant publications.
• San Francisco, CA. Full time. In person.
• Compensation. Base pay: $150,000-$250,000 per year. Base pay varies with job-related knowledge, skills, and experience.
• Experience: Any (new grads ok)
• Visa: Will sponsor