Optimized RAG Pipeline
Configurable retrieval pipeline with evaluation tooling and reranking optimization.
MLRAGSystems
Key ResultReduced p95 latency by 28% while increasing retrieval recall@10 by 11%.
Home // Technical Portfolio
ML Systems + Research Engineering
I design and benchmark learning systems with an emphasis on measurable tradeoffs, reproducible evaluation, and practical deployment constraints.
Featured Technical Projects
Transformer Implementation From Scratch
End-to-end transformer reimplementation with component-level ablation tests.
DeepLearningNLPReproducibility
Key ResultMatched 98% of baseline perplexity while exposing bottlenecks in attention kernels.
Continual Learning Adapter Experiments
Adapter-based continual learning experiments across shifting domain tasks.
ContinualLearningAdaptersEvaluation
Key ResultImproved retention by 19% versus full-finetuning baseline under domain shift.
Focus Areas
- ML Systems
- Retrieval-Augmented Generation
- Continual Learning
Research Timeline
- Built configurable RAG pipeline and latency benchmarking suite.
- Implemented transformer stack from scratch with ablations.
- Ran adapter-based continual learning experiments on domain shifts.