Postdoctoral Scholar - Research Associate

The newly established Dogra Lab () at USC invites applications for two Postdoctoral Scholar – Research Associates at the intersection of artificial intelligence (AI), mechanistic modeling, and quantitative systems pharmacology (QSP). Funded by an NIH R, our group develops predictive frameworks that integrate advanced AI/ML methods with multiscale mechanistic models of disease biology and drug action to inform drug development and clinical pharmacology in cancer, vaccines, infectious diseases, nanomedicine, and drug delivery systems.

Led by Dr. Prashant Dogra, a computational medicine scientist with expertise in mechanistic modeling and quantitative pharmacology, the lab is building innovative tools to accelerate clinical translation and support drug development.

Joining the Dogra Lab offers a unique opportunity to help build a new lab from the ground up, shape research directions, and grow into leadership roles in academia, pharma/biotech, or entrepreneurship.

Why join us?

• Innovation: Contribute to cutting-edge research at the interface of AI/ML and mechanistic modeling. Depending on your track, you may focus on:
• Track A (AI/ML): Developing physics-informed neural networks (PINNs) for integrating mechanistic constraints into ML frameworks, and creating LLM-based agents to assist with mechanistic model construction and knowledge curation.
• Track B (Mechanistic modeling): Building and analyzing multiscale models that capture biological plausibility and connect with AI/ML frameworks to address complex therapeutic challenges.
• Impact: Contribute to research that aligns with NIH and FDA priorities in advancing AI and New Approach Methodologies (NAMs) to reduce reliance on animal testing and accelerate drug development, while also opening translational and deep-tech commercialization opportunities.
• Training: Access specialized courses, workshops, and USC’s strong ecosystem in model-informed drug development (MIDD), PBPK modeling, clinical pharmacology, and pharmacometrics.
• Mentorship: Receive personalized guidance from a tenure-track PI and NIH R awardee (4), with cross-disciplinary training and a proven record of helping trainees achieve high-impact publications and successful career transitions. Support includes structured feedback in publishing, grant writing, and professional networking.
• Independence and funding: Build your research independence through opportunities to apply for fellowships and K awards, present at national and international conferences, and develop skills aligned with tenure-track opportunities. Postdoctoral scholars targeting careers in pharma or consulting will benefit from tailored networking and professional guidance.

Expectations

We seek committed postdoctoral scholars (3-year horizon) aiming for tangible outcomes, independence, and impact.

Tracks available:

Track A – AI/ML
Responsibilities:

• Develop and apply ML/DL methods to address scientific problems in pharmacology and medicine.
• Build and adapt AI-assisted tools (e.g., LLM-based agents) to support mechanistic model development and biomedical knowledge integration.
• Implement scientific ML approaches such as physics-informed neural networks (PINNs) and neural ODEs to couple ML frameworks with mechanistic models.
• Collaborate closely with the mechanistic modeling team to ensure outputs are biologically and clinically meaningful.
• Contribute to PI-led grant applications and mentor undergraduate/graduate students.

Qualifications:

• Required:
• PhD in Computer Science, AI, Data Science, Statistics, or related.
• Strong skills in machine learning and deep learning, with a fundamental understanding of LLMs.
• Proficiency in Python programming and major ML/DL frameworks (e.g., PyTorch, TensorFlow).
• Solid understanding of optimization and regularization methods for training complex neural networks.
• Practical knowledge of interpretability methods to ensure ML outputs are meaningful in scientific contexts.
• Preferred:
• Background in biomedical data, healthcare, or AI for life sciences.
• Experience with parallel computing.
• Familiarity with scientific machine learning approaches (e.g., physics-informed neural networks, neural ODEs, operator learning) and their application to dynamical systems.

Track B – Mechanistic Modeling
Responsibilities:

• Build and analyze dynamical system models (multiscale, QSP, PBPK, PK-PD).
• Apply numerical methods, optimization, and parameter estimation to calibrate models to experimental/clinical data.
• Perform sensitivity and uncertainty analyses to assess robustness and identify key drivers of system behavior.
• Conduct steady-state and stability analyses where relevant to biological interpretation.
• Collaborate with the AI/CS team to embed mechanistic constraints into ML/DL frameworks.
• Contribute to PI-led grant applications and mentor undergraduate/graduate students.

Qualifications:

• Required:PhD in Computational Biology, Pharmacometrics, QSP, Applied Math, Biophysics, Chemical/Biomedical Engineering, or related.Strong experience in ODE/PDE modeling and simulation (MATLAB, Python, or R).Experience with numerical methods, optimization, parameter estimation, and sensitivity and uncertainty analysis of dynamical systems.
• Preferred:
• Prior experience applying models to biological or clinical systems/data.
• Experience with model reduction techniques to simplify complex mechanistic models.
• Familiarity with PBPK/QSP frameworks and pharmacometrics tools (NONMEM, Monolix, Simcyp, GastroPlus).

Application instructions

Submit:

CV Up to 3 representative publications or preprints (first-author or collaborative). Cover letter (indicate track: AI/ML or Mechanistic modeling and briefly describe your contribution to the representative publications you include). Names and contact information of 3 references (letters not required at this stage).

Shortlisted candidates will first be invited for a Zoom interview with the PI. Selected candidates will then be asked to give a scientific presentation (via Zoom) to the PI and team. Letters of recommendation will be requested after this stage.

Openings are available immediately. Applications will be reviewed on a rolling basis until the positions are filled. We welcome applications from all qualified candidates who share our vision of advancing science to improve human health.

The annual salary range for this position is $, - $,. When extending an offer of employment, the University of Southern California considers factors such as (but not limited to) the scope and responsibilities of the position, the candidate’s work experience,
education/training, key skills, internal peer equity, federal, state, and local laws, contractual stipulations, grant funding, as well as external market and organizational considerations.

Qualifications:•Required: • PhD in Computer Science, AI, Data Science, Statistics, or related. • Strong skills in machine learning and deep learning, with a fundamental understanding of LLMs. • Proficiency in Python programming and major ML/DL frameworks (e.g., PyTorch, TensorFlow). • Solid understanding of optimization and regularization methods for training complex neural networks. • Practical knowledge of interpretability methods to ensure ML outputs are meaningful in scientific contexts. • Preferred: • Background in biomedical data, healthcare, or AI for life sciences. • Experience with parallel computing. • Familiarity with scientific machine learning approaches (e.g., physics-informed neural networks, neural ODEs, operator learning) and their application to dynamical systems. Track B – Mechanistic Modeling Responsibilities: • Build and analyze dynamical system models (multiscale, QSP, PBPK, PK-PD). • Apply numerical methods, optimization, and parameter estimation to calibrate models to experimental/clinical data. • Perform sensitivity and uncertainty analyses to assess robustness and identify key drivers of system behavior. • Conduct steady-state and stability analyses where relevant to biological interpretation. • Collaborate with the AI/CS team to embed mechanistic constraints into ML/DL frameworks. • Contribute to PI-led grant applications and mentor undergraduate/graduate students. Qualifications: • Required: • PhD in Computational Biology, Pharmacometrics, QSP, Applied Math, Biophysics, Chemical/Biomedical Engineering, or related. • Strong experience in ODE/PDE modeling and simulation (MATLAB, Python, or R). • Experience with numerical methods, optimization, parameter estimation, and sensitivity and uncertainty analysis of dynamical systems. • Preferred: • Prior experience applying models to biological or clinical systems/data. • Experience with model reduction techniques to simplify complex mechanistic models. • Familiarity with PBPK/QSP frameworks and pharmacometrics tools (NONMEM, Monolix, Simcyp, GastroPlus).