hey, I'm —
Shubham Pareek.
ML Engineer · Data Scientist
I build applied ML systems and the data pipelines behind them.
Columbia M.S. Data Science, graduating December 2026. I completed a summer internship at VeYou, building BigQuery analytics workflows for internal teams and partners. Earlier: clinical NLP at CUIMC and production GCP systems at Cognizant.
AI AgentsFeatured
Ask a cricket question and inspect the tools behind the answer. Gemini selects endpoints for player statistics, matchups, match analysis, and charts.
Every tool call exposes its arguments and structured result beside the answer.
- Python
- FastAPI
- Gemini
- LiteLLM
NLPFeatured
Turn synthetic health journals into traceable symptom signals, trends, and visit summaries. Every extracted signal retains its source text and evidence span.
A source-first pipeline from journal entry to an immutable, reviewable report.
- Next.js
- TypeScript
- PostgreSQL
- Drizzle
AI AgentsFeatured
Practice interviews with resume-specific questions, gap detection, and adaptive follow-ups using retrieval and a fine-tuned language model.
Resume-aware interviews with 18 gap types and inspectable, persistent session state.
- Python
- FastAPI
- Mistral-7B
- LoRA/PEFT
A few highlights from my work
2 Google Cloud certifications
Associate Cloud Engineer · Professional Cloud DevOps Engineer
BigQuery + Dataform
Data pipelines and analytics at VeYou
13M+ observations
Electricity forecasting across 368 clients
18+ identifier types
Clinical text de-identification at CUIMC
40% lower MTTR
Across 250+ production cases at Cognizant
Teaching at Columbia
Cloud Computing · Introduction to Databases