Research Scientist, LLM Evaluation & Post-Training

📋 Description

• • As a Research Scientist, LLM Evaluation & Post-Training at Centific, you will drive research that shapes how evaluation design and feedback signals improve large language models across enterprise AI products, directly impacting model quality and deployment readiness.
• • You will define and execute research agendas, develop rigorous evaluation frameworks, analyze model behavior, and collaborate with data scientists, engineers, and customer stakeholders to translate findings into scalable pipelines and actionable insights.
• • Centific is a frontier AI data foundry with over 150 PhDs and 4,000 AI practitioners, empowering enterprise clients with safe, scalable GenAI solutions through curated data, fine-tuned LLMs, and RAG pipelines, backed by a global network of 1.8 million domain experts.
• • You will have the opportunity to lead high-impact research, build reusable scientific assets, publish at top-tier venues (NeurIPS, ICML, ACL, etc.), and establish thought leadership in LLM evaluation and post-training while working in a hybrid/remote role based in Palo Alto or Seattle.