Advisor - Agent Research

Responsibilities

• Partner with scientists to build autonomous agents for molecule discovery.
• Design and build reinforcement learning (RL) environments for real discovery tasks (state/action/termination semantics).
• Curate and engineer reward functions from noisy scientific signals.
• Post-train domain models (SFT, DPO/GRPO/PPO, reward modeling, distillation) for chemistry/biology tasks.
• Integrate learned policies with domain tools (e.g., RDKit, molecular graph ML, ELN/LIMS APIs, instrument drivers) to execute DMTA tasks.
• Build evaluation infrastructure: task suites, scoring harnesses, regression tracking, and experiment tracking (e.g., MLflow).

• PhD (or MS + 3 yrs / BS + 5 yrs) in ML, Bioinformatics, Cheminformatics, Computer Science, or related field, with demonstrated wet-lab collaboration/hands-on experience.
• 1–2 years applying AI/ML to scientific domains (biology, chemistry, neuroscience, etc.).
• Hands-on experience training or post-training AI models.

• Python; deep learning frameworks (PyTorch/Tensor Flow/JAX/Hugging Face).
• RL and post-training methods (PPO/GRPO/DPO, reward modeling, RLHF/RLAIF) and libraries (e.g., TRL/verl).
• Experience with agentic AI systems; end-to-end cloud systems; AWS/Azure pipeline knowledge (Nextflow, Argo/Kubernetes).
• Publications/research contributions; mentoring experience.

• Anticipated wage: $151,500–$222,200.
• Eligible for company bonus and comprehensive benefits (e.g., 401(k), medical/dental/vision, flexible benefits, life insurance, time off, well-being benefits).