2027 Future Talent Program - Computer Scientist - Agentic & Augmented Authoring Systems - Co-op

MSD; Upper Gwynedd Township (Montgomery County); On-site; USD 39,000 - 111,000; Full time

Benefits offered by this job

Hands-on AI & cloud tech

Mentorship from senior data scientists

Collaborative team environment

Job summary

MSD is seeking a Computer Science Co‑op for a six‑month role within the Digital Operations and Innovation team. You will help build an agentic, augmented authoring system to modernize nonclinical drug safety reporting, integrating diverse data sources into consistent templates for scientists.

The role emphasizes NLP, orchestration frameworks (LangChain, LlamaIndex, CrewAI), Python development, and API integration. You will contribute in sprints, with opportunities for future full‑time roles.

Qualifications

• Pursuing a PhD in CS or AI or a highly quantitative field.
• Strong Python coding skills with clean, modular code.
• Experience with NLP and structured/unstructured data formats.
• Familiarity with LLM APIs, orchestration frameworks, and tool use.
• Analytical research skills for noisy/unstructured data.
• Excellent communication bridging AI development and science.

Responsibilities

• Design and implement agentic workflows and orchestration pipelines to automate retrieval, synthesis, and formatting of nonclinical safety data.
• Develop robust data extraction pipelines in Python to parse diverse data sources.
• Evaluate and benchmark LLM outputs for accuracy and formatting against templates.
• Collaborate with data scientists and SMEs to automate manual steps into agent tools.
• Participate in agile sprints and maintain production-grade documentation via GitHub.

Skills

Python

NLP

LLM APIs

Prompt engineering

Agent orchestration

Data extraction

Education

PhD in Computer Science

Tools

LangChain

LlamaIndex

CrewAI

AWS

GCP

GitHub

Vector databases

Job description

Job Description

The Future Talent Program features Co‑operative (Co‑op) education that lasts up to 6 months and will include one or more projects. These opportunities in our Research and Development Division can provide you with great development and a chance to see if we are the right company for your long‑term goals.

Nonclinical Drug Safety helps advance high‑quality drug candidates into development by defining the nonclinical safety and selectivity of lead compounds. Nonclinical Drug Safety employees evaluate Lead Op candidates and preclinical toxicity of drug development candidates, providing a mechanistic understanding of drug‑induced toxicity and assessing implications for human safety. Nonclinical Drug Safety provides collaborative research in animal model development, veterinary medical and animal care, and research facility management. Nonclinical Drug Safety also responds to regulatory questions in support of drug registration.

The Digital Operations and Innovation (DOI) team within NDS Operations comprises a talented group of data scientists dedicated to leveraging scientific and operational data to reduce administrative burden, improve the findability and accessibility of data, and discover and implement innovative applications of AI to modernize and advance our business.

Position Overview:

We seek a talented and motivated Computer Science Co‑op to join our team for a six‑month role. This position will contribute to our efforts to develop an agentic, augmented authoring system supporting Nonclinical Drug Safety. The goal of this effort is to drive towards a “zero‑draft” process that retrieves, combines, and formats key data from structured, semi‑structured, and unstructured sources into a consistent template for our scientists. The ideal candidate will actively participate in regular sprints to design and refine agents, propose creative solutions to agent‑based workflows, and work closely with scientific and operational SMEs.

In this role, you will be a valued contributor to a visible and necessary effort aimed at modernizing how nonclinical safety fulfills its critical role in the development of safe medicines for our patients. Your work will help produce stable, reliable, and consistent AI‑driven pipelines that accelerate our reporting timelines and build technology at the cutting edge of our field.

The ideal candidate will have experience with the principles of Natural Language Processing (NLP) in addition to agent‑based concepts including orchestration frameworks (such as LangChain, CrewAI, LlamaIndex, or equivalent), tool calling, and API integration. Strong Python coding and documentation skills are essential. Familiarity with AWS and Google services, GitHub, LLMs, and vector databases is an additional advantage. Familiarity with nonclinical drug safety, report authoring, and summarization is a strong advantage.

Key Responsibilities:

• Design and implement agentic workflows and orchestration pipelines to automate the retrieval, synthesis, and formatting of nonclinical safety data.
• Develop robust data extraction pipelines in Python to parse and clean structured, semi‑structured, and unstructured data from diverse scientific sources.
• Evaluate and benchmark LLM outputs for accuracy, formatting consistency, and alignment with strict nonclinical reporting templates.
• Collaborate closely with fellow data scientists and scientific SMEs to translate manual document‑authoring steps into automated, step‑by‑step agent tools and skills.
• Participate in agile sprints, contribute to team code reviews, and maintain clean, production‑grade documentation via GitHub.

Required Qualifications:

• Education: Currently pursuing a PhD in Computer Science, Data Science, Artificial Intelligence, Software Engineering, or a highly quantitative, research‑focused field.
• Programming: Strong proficiency in Python programming with a focus on clean, modular, and well‑documented code.
• Data structures: Solid understanding of data structures and proficiency in manipulating structured, semi‑structured, and unstructured data.
• AI & Orchestration: Hands‑on experience working with LLM APIs, prompt engineering, agentic tool use, and orchestration frameworks (LangChain, LlamaIndex, CrewAI, etc.).
• Problem Solving: Strong analytical and research skills, particularly when dealing with noisy, unstructured, or ambiguous data sources.
• Collaboration: Exceptional communication skills with the ability to bridge the gap between technical AI development and scientific domains.

Preferred Qualifications:

• Experience with vector databases and document embedding techniques.
• Experience with text processing, OCR, and principles of NLP and NLP evaluation (ROUGE, BLEU, etc.).
• Experience with cloud services (AWS/GCP) and version control using Git/GitHub.
• Exposure to building lightweight developer UIs and dashboards for analytics and prototype/demo usage.

What You’ll Gain:

• Cutting‑Edge Experience: Deep, hands‑on experience building and deploying production‑grade LLM agents and advanced Retrieval‑Augmented Generation (RAG) pipelines.
• Highly Valued Domain Knowledge: Practical knowledge of how to navigate enterprise data engineering and AI development within a secure, highly regulated healthcare environment.
• Real‑World Impact: A clear understanding of how modern generative AI accelerates drug safety reporting, directly shortening timelines to bring life‑saving medicines to patients.

What We Offer:

• Hands‑on experience with cutting‑edge AI and cloud technologies
• Mentorship from experienced data scientists and software engineers
• Collaborative and inclusive team environment
• Potential for future full‑time opportunities with our Company

Please note that this position may be closed before the posted end date or may remain open longer, at the discretion of the company.

Salary range: The salary range for this role is $39,108 through $111,111.

Our company is committed to inclusion, ensuring that candidates can engage in a hiring process that exhibits their true capabilities.

As an Equal Employment Opportunity Employer, we provide equal opportunities to all employees and applicants for employment and prohibit discrimination on the basis of race, color, age, religion, sex, sexual orientation, gender identity, national origin, protected veteran status, disability status, or other applicable legally protected characteristics. As a federal contractor, we comply with all affirmative action requirements for protected veterans and individuals with disabilities. For more information about personal rights under the U.S. Equal Opportunity Employment laws, visit:

We are proud to be a company that embraces the value of bringing together, talented, and committed people with diverse experiences, perspectives, skills and backgrounds. The fastest way to breakthrough innovation is when people with diverse ideas, broad experiences, backgrounds, and skills come together in an inclusive environment. We encourage our colleagues to respectfully challenge one another’s thinking and approach problems collectively.

San Francisco Residents Only: We will consider qualified applicants with arrest and conviction records for employment in compliance with the San Francisco Fair Chance Ordinance.

Los Angeles Residents Only: We will consider for employment all qualified applicants, including those with criminal histories, in a manner consistent with the requirements of applicable state and local laws, including the City of Los Angeles’ Fair Chance Initiative for Hiring Ordinance.

Employee Status:

Intern/Co‑op (Fixed Term)

Relocation:

No relocation

Visa Sponsorship:

No

Travel Requirements:

No Travel Required

Flexible Work Arrangements:

Not Applicable

Shift:

1st - Day

Valid Driving License:

No

Hazardous Materials:

N/A

Job Posting End Date:

10/30/2026

A job posting is effective until 11:59:59PM on the day BEFORE the listed job posting end date. Please ensure you apply to a job posting no later than the day BEFORE the job posting end date.