Job Description
This is a Contract position with a 3 months end date from start date
Job Function Summary
Engaged in the development and automation of AI-driven regulatory science systems and population pharmacokinetics modeling workflows. Responsibilities include assisting with constructing large language models (LLMs) using Retrieval-Augmented Generation (RAG) and benchmarking their performance against leading models such as ChatGPT and Gemini. Support in designing, implementing, and maintaining automated pipelines for model construction, optimization, and result reporting. Additionally, responsible for assisting with developing and managing data sharing and archiving systems to support research projects, ensuring data integrity, accessibility, and reproducibility. Work supports full-cycle system design, implementation, evaluation, maintenance, and documentation.
Generic Scope
Entry-level professional with limited prior experience; learns to use professional concepts to resolve problems of limited scope and complexity; works on assignments that are initially routine in nature, requiring limited judgment and decision making. Employees at this level are expected to acquire the skills and knowledge to perform more advanced work following an agreed upon time in position, through defined training and development planning.
Custom Scope
Under general supervision, applies professional computational and data science concepts to the development and automation of AI-driven modeling systems in regulatory science and pharmacokinetics. Assist with projects of moderate scope involving large language model (LLM) construction using RAG frameworks, model performance benchmarking, and workflow automation for population pharmacokinetics modeling. Follows established research and development procedures to collect, analyze, and manage scientific data. Contributes to the design and maintenance of data sharing and archiving systems to ensure research reproducibility and compliance with institutional policies.
Responsibilities
% of timeEssential Function (Yes/No)Key Responsibilities (To be completed by Supervisor)
40% Yes
Assisting with constructing a large language model of regulatory science using RAG, compares in-house model performance with the benchmark LLMs such as ChatGPT and Gemini.
40% Yes
Assist with automating the model construction, optimization and result reporting of population pharmacokinetics modeling.
20% Yes
Support designs and maintains a data sharing and archiving system for research projects
Qualifications
Required Qualifications
- Bachelor's degree in related area and / or equivalent experience / training.
- Skill in programming languages commonly used in AI and data science (e.g., Python, R) and in the use of machine learning libraries and APIs.
- Demonstrated effective communication and interpersonal skills.
- Demonstrated ability to communicate technical information to technical and non-technical personnel at various levels in the organization.
- Self-motivated and works independently and as part of a team. Able to learn effectively and meet deadlines.
