Hi 👋, I'm Sarthak Khandelwal

Data Scientist | Automation Specialist | LLMs, Cloud Platforms

Previously a Data Engineer at FiftyFive Technologies, I worked on preparing a SQL-based ETL pipeline for business insights and enabled data-driven decision-making. I'm passionate about transforming data into actionable insights to address real-world challenges. I completed my undergraduate degree in Computer Science from Medi-Caps University. My professional journey in Machine Learning (ML) and Data Science began during my sophomore year when I joined a technical club titled Students' Technical and Innovation Club (STIC). Since then, I have undertaken numerous projects and internships, honing my skills and contributing to impactful solutions. Driven by a commitment to continuous learning, I pursued a master's degree to deepen my understanding of ML and Data Science and explore how these technologies drive business innovation. I am particularly excited about leveraging my expertise to improve real-world outcomes through data-driven approaches.

As a Research Assistant at Northeastern University, I worked on formulating a dialogue-based voice assistant titled Auxel that enable blind and low vision individuals in performing data analysis efficiently through interactions with a GPT-3.5 turbo model. This groomed my skills in Natural Language Processing and understanding of Large Language Models. Later during Spring 2024, I took a course titled DS 5983: Large Language Models where I gained in-depth understanding of LLMs and became aware of the current trends in this field.

While working at Mayo Clinic, I operationalized an ETL pipeline integrating VertexAI, BigQuery, and Cloud Storage to process lab reports of patients with Lupus Anticoagulant and generate interpretations which is further streamed to a Dash Application through BigQuery enabling easier analysis for Hematopathologists. Furthermore, I acquired further experience with Data Cleaning and Pre-Processing by migrating 5000+ unstructured Word files into a GeoDatabase for Panelboards Circuit Reports.

• 🌱 Currently working on instituting model pipelines on Cloud Platforms.
• 👨‍💻 Participating in hackathons, competitions, events, and seminars.
• 📫 Experimenting and grooming understanding of LLM-based agents and Trustworthy AI.

Explore More Projects

Kaggle Badges

Programming Workbench:

Data Science Workbench:

Database

Data Science Frameworks

Cloud Platforms

Relevant Coursework

Let's Connect!