Data Scientist: AI-Driven Scientific Insights

Chemical Abstracts Service; Columbus (OH); On-site; USD 110,000 - 150,000; Full time

Job summary

CAS Columbus, OH seeks a Data Scientist on the Data Analytics and Insights team to build AI-powered features for scientific information products. You'll collaborate with data engineers, product managers, and domain experts to deliver production-grade pipelines.

The role requires dual-domain expertise in science and software engineering, with proficiency in Python, LangChain, RAG, and cloud deployment. You'll work on models predicting properties, toxicity, and developability, grounded in CAS

Qualifications

• Requires two-domain expertise in science and software engineering.
• Demonstrates strong Python programming and software practices.
• Experience with LangChain, LangGraph, and cloud deployment is required.

Responsibilities

• Develop and deploy agent-based workflows, RAG pipelines, and LLM-powered features using Python and LangGraph/LangChain.
• Build and deploy ML models that ship inside CAS products (property, toxicity, developability).
• Ground AI features in CAS scientific content and validate outputs for accuracy and usefulness.
• Engineer for production: tests, docs, safeguards, CI/CD, and containerized development.

Skills

Python

LangGraph/LangChain

LLMs / AI development

Software engineering fundamentals

ML / data science

Education

Bachelor's degree in a scientific discipline

Tools

AWS

Azure

GCP

Job description

CAS Columbus, OH seeks a Data Scientist on the Data Analytics and Insights team to build AI-powered features for scientific information products. You'll collaborate with data engineers, product managers, and domain experts to deliver production-grade pipelines.

The role requires dual-domain expertise in science and software engineering, with proficiency in Python, LangChain, RAG, and cloud deployment. You'll work on models predicting properties, toxicity, and developability, grounded in CAS