🎯 Data Scientist & Data Engineer with 3 years of industry experience building ML models, Generative AI applications, scalable data pipelines, and cloud-native systems on AWS, now pursuing an MS in Information Management (Data Science & Analytics) at UIUC.
I love solving real-world problems at the intersection of Machine Learning,Generative AI, LLMs, and Data Engineering, and turning messy data into impactful insights.
- 🔭 Currently pursuing: MS in Information Management @ UIUC
- 🧠 Passionate about: LLMs, Generative AI, Data Engineering, Applied ML
- 💼 Previously: Senior Data Engineer (Business Intelligence), Piramal Finance
- 🤝 Open to: Collaborations in AI, ML, LLMOps, and Data Platform Engineering
- 🌍 Location: Champaign, IL (open to relocate)
- ⚡ Fun fact: I enjoy exploring system design + trying out new ML frameworks!
- Built an LLM-powered SQL optimization agent → reduced query latency 60% & compute cost 25%
- Designed an automated Kafka–Airflow loan pipeline → enabled real-time MIS, driving 60% business growth
- Developed a GenAI-powered Data Catalog agent using GPT + Snowflake metadata → cut onboarding time 40%
- Built a 250+ column Snowflake data mart with PySpark, AWS Lambda, S3 → reduced manual prep time 70%
- Improved data reliability 25% through automated quality checks
- Reduced manual reporting work by 5+ hrs/week with ML-driven ETL automation
3D Model Rendering Using Three.js for Campus Visualization
IEEE ICAST, 2022
Link: https://ieeexplore.ieee.org/document/10039553
| Python | R | NumPy | Pandas | PyTorch | TensorFlow |
|---|---|---|---|---|---|
 |
 |
 |
 |
 |
 |
| AWS | Snowflake | Airflow | Spark | Kafka |
|---|---|---|---|---|
 |
 |
 |
 |
 |
| HuggingFace | OpenAI |
|---|---|
 |
 |
| Tableau | Matplotlib |
|---|---|
 |
 |
| MySQL | PostgreSQL | Git | GitHub | Jira | JavaScript |
|---|---|---|---|---|---|
 |
 |
 |
 |
 |
 |
🌐 LinkedIn: https://www.linkedin.com/in/shithil-shetty
📧 Email: shetty7@illinois.edu