Data Engineer
Data Engineer with experience building scalable healthcare data integration and ETL pipelines, optimizing Apache Spark workloads, and developing AI and RAG systems.
Abacus Insights
Sep 2025 - Present
Delivered enterprise-grade data integration solutions for a Medicaid data modernization program; built ETL pipelines processing 50–120 GB/day of healthcare data; implemented Medallion Architecture; optimized PySpark jobs to reduce execution time by approximately 44%; achieved a 99.5% pipeline success rate; reduced AWS S3 storage costs by 20%.
UPSILON AI
Mar 2025 - Sep 2025 · Remote, Singapore
Developed multimodal AI agents using LLMs and vector databases; improved response relevance by 30% through prompt engineering and embeddings; built RAG pipelines integrating Pinecone vector search with LLMs.
B.E., Information Science and Engineering
Dec 2021 – Jun 2025
CGPA: 8.5/10
PCMB
Jun 2019 – Aug 2021
96.67%; SSLC: 96.50%
Built and deployed a production-grade AI SaaS platform that converts websites into conversational agents. Engineered an end-to-end RAG pipeline handling 100+ documents per knowledge base, scaled to 500+ customers, generated $2K+ in revenue, reduced API costs by 30%, and achieved under 500 ms semantic search latency with Supabase.
Built an AI-driven web app to detect skin conditions and recommend personalized skincare products using RAG, web scraping, and Next.js.
Built a voice-driven AI professor enabling real-time interactive learning as part of a team shortlisted in the Global AI Hackathon involving MIT, OpenAI, and ElevenLabs.