AI Research Engineer
GENERATIVE MODELS
OPTIMIZATION
VISUALIZATION
Trained in computer science, I specialized in optimization techniques and AI. Recently, I advanced diffusion models for generative antibody design using negative guidance. I think visually, build clean systems, and ship research-grade work with measurable impact.
ARTIFICIAL INTELLIGENCE
Negative guidance with an auxiliary model to improve sample quality without increasing dataset size.
Started from existing model. Introduced guidance technique from image diffusion. Improved sampling strategy and trained an auxiliary model on synthetic data using a custom dataloader with LMDB for efficient access. Applied negative guidance at inference to steer generation toward higher-quality samples. Evaluated using RMSD, AAR, and ESM-2 Perplexity Pseudo Log Likelihood for biological plausibility.
OPERATIONS RESEARCH
Sequence jobs so that you minimize the amount of tool switches you need to do. Solved using local search.
Introduced a novel local search operator that does ruin and recreate. It ruins and recreates by using a strategy that clusters jobs and best inserts local sequences. Aided by a well established constructive heuristic and guided using simulated annealing as meta heuristic.
- 2025
Imagenet Data Insights with VGG16
Interactive Dash app to inspect VGG16: layer activations, per-layer t-SNE embeddings, and class heatmaps (CAM/Grad-CAM), on ImageNet subsets.
- 2021
Funnler
Funnler is a virtual queueing platform for large events: a React Native attendee app plus a React organizer dashboard with simulations and live queue insights, backed by scalable Python microservices on Kubernetes. I led the eight-person team and contributed to the front-end, scheduler, and product design.
