Advisor - Agent Research

Scorpion Therapeutics; Indianapolis (IN); On-site; USD 120,000 - 180,000; Full time

Benefits offered by this job

Company bonus

401(k)

Pension

Vacation

Medical/dental/vision/prescription

Flexible benefits

Life insurance

Time off

Well-being benefits

Job summary

Scorpion Therapeutics is seeking an AI/ML scientist to work with scientists on autonomous agents for molecule discovery. You will design RL environments, curate reward signals, and post-train models for chemistry/biology tasks, integrating with RDKit and ELN/LIMS tools.

The role emphasizes hands-on model training, tool integration, and evaluating task suites with MLflow, in a collaborative scientific setting at Scorpion Therapeutics.

Qualifications

• PhD or MS/BS with lab collaboration/hands-on experience.
• ~1–2 years applying AI/ML in scientific disciplines (biology, chemistry, neuroscience, etc.).
• Hands-on experience training/post-training AI models.

Responsibilities

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

Skills

Python

PyTorch

TensorFlow

JAX

HuggingFace

RL methods

Reward modeling

Agent SDK

Molecular representation learning

Generative chemistry

Cloud

Kubernetes

Education

PhD or MS/BS with related field

Tools

OpenAI Agent SDK

LangChain

Smol agents

TRL

GitHub portfolio

AWS

Azure

Nextflow

Argo

Kubernetes

Job description

Responsibilities:

• Partner with scientists to build autonomous agents for molecule discovery tasks.


• Design and build reinforcement learning (RL) environments with appropriate state/action/termination semantics for discovery.


• Curate and engineer reward functions from noisy scientific signal.


• Post-train domain models (SFT, DPO/GRPO/PPO, reward modeling, distillation) on chemistry and biology tasks.


• Integrate learned policies with domain tools (RDKit, molecular graph ML, ELN/LIMS APIs, instrument drivers) to execute real DMTA tasks.


• Build evaluation infrastructure (task suites, scoring harnesses, regression/experiment tracking e.g., MLflow).

Basic Qualifications:

• 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 in scientific disciplines (biology, chemistry, neuroscience, etc.).


• Hands-on experience training/post-training AI models.

Preferred Qualifications/Skills:

• Python; deep learning frameworks (PyTorch, TensorFlow, JAX, HuggingFace).


• RL and post-training methods (PPO, GRPO, DPO, reward modeling, RLHF/RLAIF) and libs (TRL, verl, or equivalents).


• Molecular representation learning/generative chemistry/protein-nucleic acid models.


• Agentic AI systems experience (OpenAI/Anthropic Agent SDK, LangChain, Smol agents).


• Cloud end-to-end system experience (APIs/frontends/agent platforms); GitHub portfolio a plus.


• Cloud-native pipeline knowledge (AWS/Azure), Nextflow/Argo on Kubernetes.


• Research contributions/publications; mentoring experience.

Benefits:

• Eligible for company bonus; 401(k), pension, vacation; medical/dental/vision/prescription; flexible benefits; life insurance; time off/leave; well-being benefits (EAP/fitness/clubs).