I’m currently working on AI at Aqxle, building AI agents that help cut through marketing complexity, turning time-consuming analysis into fast, actionable insights.
Over the years, I’ve worked across healthcare, cybersecurity, and now marketing tech - always staying close to the code. Whether it’s building scalable systems, training models, or figuring out the right abstractions, I enjoy working at the intersection of applied ML and product impact. I’ve led and built projects from the ground up involving LLMs, data pipelines, and real-time systems, and more. I pick up new tools fast and care deeply about clean design and practical problem-solving.
If you’re working on something interesting or just want to chat about AI, feel free to reach out.
Languages & Databases
AI & ML Frameworks
Tools & Platforms
Experience
AI Research Engineer @ Aqxle
- Building AI Agents for the marketing flywheel that helps marketers get from data to insights very quickly, using a patent-pending approach to taxonomy normalization.
Manager - Data Science & AI Applications @ VedTechBio
- Developed and delivered RxAgentAI, a Generative AI platform for drug research & discovery, integrating features like Report Generation and AI Researcher.
- Built Autonomous AI Agents using reasoning-based LLMs and multi-agent frameworks (Langgraph, PydanticAI) for domain-specific tasks.
- Scaled an AI-powered analytics platform delivering insights from 200M+ papers and 100+ public data sources for big pharma.
Senior Data Scientist @ Alphameld
- Built an Entity & Relation Extraction pipeline with Entity Linking, improving prediction accuracy by >25% over rule-based systems.
- Led development of ChatAlphaMeld, a biomedical multi-agent RAG tool that reduced hypothesis generation time by over 4x.
- Developed AlphaClinMeld, a clinical trial design platform using LLMs with a human-in-the-loop feedback system.
Data Science Analyst (prev. Intern) @ Netenrich
- Deployed text classification models (AlBERT, chars2vec) to filter content for a cyber-intelligence platform.
- Built NLP multi-task models to improve SLA response times and a BERT-based NER model that doubled the accuracy of previous systems.
- Designed a probabilistic Bayesian network to accelerate root cause analysis from hours to minutes.
Projects
OCDify
The offline AI-powered Mac file organization tool that automatically sorts, categorizes, and declutters your desktop. Transform your chaotic file system into an organized workspace instantly—all while keeping your data 100% private on your Mac.
reportAI
A Python-based tool that generates comprehensive PDF research reports from conversational text using Generative AI.
NER-RE
A Named Entity Recognition + Entity Linker + Relation Extraction Pipeline built using spacy v3. Given a text, the pipeline will extract entities from the text as trained and will disambiguate the entities to its normalized form through an Entity Linker connected to a Knowledge Base and will assign a relation between the entities.
intelliweb-GPT
An intelligent QA module using GPT models to provide accurate, relevant, and recent answers from Google News/Web, or directly from its own knowledge base.
proxy_configuration
System wide proxy configuration in a single script with options to add, remove proxy and restore system default proxy configuration.
Get In Touch
I'm always open to discussing new projects, creative ideas, or opportunities to be part of an ambitious vision. Feel free to reach out.