Experience

Senior AI/ML Scientist — Merck & Co., Inc.

Sep 2024 – Present · South San Francisco, CA
  • Develop generative models for small-molecule drug design, transitioning from SMILES-based RNN approaches to GFlowNet-based architectures that generate molecules over validated reaction templates using commercially available building blocks. Focus on R-group optimization, core-hopping, and knowledge-based design with multi-stage curriculum learning.
  • Built an automated benchmarking and deployment pipeline for ADMET property prediction spanning gradient-boosted trees, message-passing neural networks, and foundation models. Models are deployed directly to medicinal chemists for real-time predictions during design cycles.
  • Mentored interns and contributed to shared ML platform infrastructure across drug discovery teams.

Graduate Researcher — Caltech, Zhen-Gang Wang Group

Jan 2022 – Aug 2024 · Pasadena, CA
  • Combined enhanced-sampling molecular dynamics with unsupervised deep learning to map phase diagrams for proteins and polymers in solution. Identified precipitation mechanisms and quantified structure-activity relationships.
  • Developed generative diffusion models for polymer design. Built an automated pipeline to compute binding free energies at solid-liquid interfaces.
  • Managed high-performance computing resources using Slurm and Ansible, increasing computational throughput for the research group by 10x.

Graduate Researcher — Caltech, John F. Brady Group

Sep 2019 – Dec 2021 · Pasadena, CA
  • Built CPU and GPU parallelized simulations of suspended bodies in C++, CUDA, and OpenMP for computational fluid dynamics study of self-propelled swimmers and collective phenomena.
  • Developed theoretical models of hydrodynamic interactions for self-propelled bodies across viscous and inviscid flow regimes. Found universal symmetries linking body shape changes to swimming efficiency.

Research Assistant — UC Berkeley, Kranthi K. Mandadapu Group

Aug 2017 – May 2019 · Berkeley, CA
  • Introduced the Scriven-Love number, a dimensionless ratio comparing out-of-plane forces from intramembrane viscous stresses to elastic bending forces. Showed that viscous response cannot generally be neglected in biological membrane dynamics.
  • Modeled phospholipid bilayer dynamics using differential geometry and nonequilibrium thermodynamics. Characterized how membrane curvature couples to viscous flow within the bilayer.

Battery Cell Quality Assurance Intern — Nissan (Automotive Energy Supply Corporation)

May 2018 – Aug 2018 · Smyrna, TN
  • Designed an automated battery quality control system for testing 25,000 cells/day on electrochemical stability, producing annual savings of $50k.
  • Diagnosed electrode misalignment issues contributing to cell failures and proposed tolerance revisions that cut $55k in annual material scrap costs.

Battery Management Systems Intern — Bosch

May 2017 – Aug 2017 · Palo Alto, CA
  • Evaluated electrode additive stability in lithium-ion batteries by analyzing dissolution under electric vehicle usage conditions, identifying key degradation mechanisms to improve battery lifetime.
  • Established a training program on plasma spectroscopy for 3 colleagues to measure trace lithium content in cycled battery components.

Research Assistant — Lawrence Berkeley National Laboratory, Nitash Balsara Group

Jun 2016 – May 2017 · Berkeley, CA
  • Characterized electrochemical properties of solid-state polymer electrolyte batteries via impedance spectroscopy across temperatures, identifying electrode degradation mechanisms.
  • Fabricated lithium metal batteries with polymer electrolytes to study the effects of molecular weight and cross-linking density on ionic conductivity, verifying theoretical predictions.