Member of Technical Staff Evals and Post Training Product

You will build infrastructure and workflows connecting model evaluation and post-training. You will scale evaluation systems, create benchmarks, improve fine-tuning experiences, investigate model results, and turn user needs into reusable product solutions.

Responsibilities

• Scale evaluation infrastructure
• Track benchmarks and reproduce published results
• Design and build new model-performance benchmarks
• Build and improve post-training and fine-tuning workflows
• Partner with users to understand needs and productize solutions

Requirements

• Software engineering or data science
• System design
• Sandbox infrastructure
• LLM evaluation
• Data science
• Model fine-tuning
• GenAI lifecycle

Benefits

• Equity