Data Engineer / Data Scientist building reliable data and ML workflows from ingestion → storage → analytics → dashboards.
- Clinical data: Co-built VaxTrack, a vaccine trial management system supporting 8,000+ participants at icddr,b; automated cleaning, validation, and reporting for research teams.
- Automation & integrations: Built Flask webhooks and API connectors to sync behavioral and marketing data into CRMs/ESPs (HubSpot, custom) with GDPR-aware processing.
- FinTech/Markets: Delivered API ingestion + warehousing for crypto/stock OHLC data, backtesting engines (Python + Excel), and Grafana dashboards for real-time KPIs.
- Dashboards & insight: Python + SQL → Superset/Grafana dashboards that reduce manual reporting by 40–60% and enable day-to-day decision making.
- ML/NLP: Classification, regression, time series, feature engineering; IEEE publication on Bengali toxic-comment classification.
Tech: Python, Pandas, NumPy, Scikit-learn, (basic) PyTorch/TensorFlow, SQL/MySQL, Flask, Django, Docker, AWS (EC2/S3/RDS), Superset/Grafana, Git, Jupyter.
What I’m looking for: Data Engineer / Data Scientist / ML Engineer roles where I can own ETL + modeling and ship useful dashboards or APIs. Open to remote.
ICDDR,B — Data Management Officer (Jan 2025 – Present)
- Built & maintained VaxTrack for 8,000+ participants; automated data validation and visit tracking.
- Authored Python ETL to clean/merge site data; reduced manual prep by 40%.
- Created Superset dashboards used by 20+ researchers for daily monitoring & reporting.
- Wrote optimized SQL+indexes for faster cohort queries on large tables.
Gobot — Python Automation & Integration Specialist (PT, Remote) (Mar 2025 – Present)
- Built Flask webhooks to capture behavioral events and sync to HubSpot/ESPs.
- Automated lead enrichment & campaign triggers; improved follow-up speed measurably.
- Implemented GDPR-aware data flows and monitoring.
Changing Digital — Data Collection Specialist (PT, Remote) (Jul 2024 – Present)
- Designed Python scraping & validation jobs for fund datasets; scheduled with cron/Docker.
- Shipped datasets powering a Fund Data Platform; automated HubSpot workflows.