Autonomous Molecular Discovery AI Scientist

Jobtailor; California (MO); On-site; USD 150,000 - 190,000; Full time

Job summary

Jobtailor is seeking a highly capable ML scientist to advance autonomous agents for molecule discovery. You will design reinforcement learning environments, engineer reward functions, and post-train models across chemistry and biology tasks.

You will integrate tools like RDKit, LIMS/ELN APIs, and instrument drivers while contributing to evaluation pipelines and MLflow tracking. The role involves collaborating with scientists, mentoring junior researchers, and presenting work to the AI community.

Qualifications

• PhD in ML, Bioinformatics, Cheminformatics, CS or related field or MS with 3+ years
• Hands-on collaboration with wet-lab or biology teams
• 1–2 years applying AI/ML to biology, chemistry, neuroscience, or related field
• Hands-on experience training or post-training AI models
• Proficiency in Python and ML frameworks
• Experience with RL and post-training methods (PPO, GRPO, DPO, reward modeling)
• Familiar with molecular representation learning or generative chemistry
• Experience building end-to-end cloud systems
• Cloud-native workflows (AWS/Azure, Nextflow, Argo on Kubernetes)
• Mentoring junior researchers or engineers

Responsibilities

• Partner with scientists to build autonomous agents for molecule discovery tasks
• Design and build reinforcement learning environments with proper state, action, and termination semantics
• Curate reward functions from noisy scientific signals
• Post-train domain models using SFT, DPO, GRPO, PPO, reward modeling, and distillation
• Integrate learned policies with domain tools (RDKit, ELN/LIMS APIs, instrument drivers)
• Build evaluation infrastructure, task suites, scoring harnesses, and experiment tracking (MLflow)
• Represent Frontier AI in the AI research community and publish work
• Evaluate external vendors, open-source projects, and academic collaborations
• Develop models and infrastructure to improve autonomous discovery and reduce DMTA turnaround
• Transition AI prototypes into production-deployed systems

Skills

Python

Reinforcement Learning

ML Frameworks

Post-Training Methods

Molecular Learning

Agentic AI Systems

Cloud Architectures

Mentoring

Publications

Education

PhD in Machine Learning

MS/BS with equivalent experience

Tools

PyTorch

TensorFlow

JAX

HuggingFace

MLflow

AWS

Azure

Nextflow

Argo

Kubernetes

Job description

Jobtailor is seeking a highly capable ML scientist to advance autonomous agents for molecule discovery. You will design reinforcement learning environments, engineer reward functions, and post-train models across chemistry and biology tasks.

You will integrate tools like RDKit, LIMS/ELN APIs, and instrument drivers while contributing to evaluation pipelines and MLflow tracking. The role involves collaborating with scientists, mentoring junior researchers, and presenting work to the AI community.