Professional Overview
I am a data Scientist with 5+ years of experience developing production oriented machine learning, multimodal AI and Generative AI solutions for healthcare and regulatory domains, with additional independent project experience building Retrieval-Augmented Generation (RAG) and agentic AI systems. Expertise in NLP, LLM/VLM fine-tuning, image classification, model evaluation, and scalable AI pipelines using PyTorch and AWS, with demonstrated impact in reducing inference cost, latency, false positives, and reviewer effort.
Experience
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Fine-tuned lightweight PyTorch vision models (DiT, ConvNeXt)
- Optimized a Sonnet-based edited-image detection pipeline.
- Built an NLP pipeline to detect novel medical device problems
- Orchestrated end-to-end data pipelines with Dagster for signal detection.
- Built BERT/PyTorch multi-label classifier to detect off-label medical-device use
Key Achievements / KPIs
- reduced token consumption by 85% and erroneous alerts by 50%.
- Built standardized ML training infrastructure using PyTorch Lightning and Hydra
- Built multimodal model reducing false-positive alerts and reviewer burden by 50%
AI Expertise
Skills
Employment Type
Description of Responsibilities
- Fine-tuned lightweight PyTorch vision models (DiT, ConvNeXt)
- Optimized a Sonnet-based edited-image detection pipeline.
- Built an NLP pipeline to detect novel medical device problems
- Orchestrated end-to-end data pipelines with Dagster for signal detection.
- Built BERT/PyTorch multi-label classifier to detect off-label medical-device use
Key Achievements / KPIs
- reduced token consumption by 85% and erroneous alerts by 50%.
- Built standardized ML training infrastructure using PyTorch Lightning and Hydra
- Built multimodal model reducing false-positive alerts and reviewer burden by 50%
Areas of Expertise
AI Product & Strategy
Translate AI capabilities into product roadmaps, define success metrics, and drive adoption across engineering and business teams.
NLP & Prompt Engineering
Build natural language processing systems, fine-tune large language models, and craft reliable production prompts for AI-powered products.
Data Science & Analytics
Extract business insights from raw data using statistical modelling, predictive analytics, A/B testing, and interactive dashboards.
