Research Engineer, Post-training & Reasoning

Cobalt builds expert reasoning data infrastructure for AI. They are seeking a Research Engineer focused on post-training and reasoning to conduct research, develop algorithms, and enhance AI models while collaborating with cross-functional teams.

Responsibilities:

• Conducting research in post-training optimization and reasoning techniques
• Developing innovative algorithms
• Collaborating with cross-functional teams to apply findings to advanced AI systems
• Analyzing complex datasets
• Enhancing AI models
• Contributing to cutting-edge R&D projects aimed at optimizing AI performance and interpretability
• Designing and running SFT, DPO, and RL (GRPO/PPO and successors) experiments on reasoning traces from our expert network
• Building benchmarks and evals that meaningfully measure clinical and adjudication reasoning
• Turning raw expert outputs into high-quality training datasets: schema design, quality controls, scaling pipelines
• Working directly with customers (frontier labs, healthcare AI companies) on bespoke data and eval engagements
• Publishing where it makes sense