AadarshPraveen
Building production-grade AI systems — from RAG pipelines to multi-agent architectures — that solve real-world problems at scale.
WhoIAm
Results-driven AI/ML Engineer and Data Scientist with 3+ years of experience designing and deploying production-grade machine learning systems, RAG pipelines and data engineering solutions across enterprise domains including real estate, municipal government, and financial services.
I specialize in building intelligent systems that understand context, retrieve knowledge, and reason across complex domains — turning cutting-edge research into reliable, production-ready products.
Experience
AI/ML Engineer
CurrentIpserLab LLC
- Building Smart Pantry — LLM-powered meal recommendation engine with OCR grocery scanning
- Architecting Supabase + Neon PostgreSQL full-stack with OAuth (Google/Apple) auth
- Designing LLM prompt pipelines for personalized recipe generation with dietary constraints
- ML model evaluation with precision/recall/F1 metrics for recommendation quality
AI Developer
EasyBee AI
- Built production RAG workflows for real estate and municipal government on AWS
- Achieved 85% accuracy with 0.52s avg latency across thousands of QA pairs
- Engineered Pinecone vector search with namespace isolation and metadata enrichment
- Implemented automated RAG evaluation framework using Python asyncio pipelines
Application Development Analyst
Accenture
- Optimized ETL pipelines with Python + Apache Spark, improving throughput by 30%
- Applied KMeans and hierarchical clustering to improve engagement metrics by 15%
- Built Power BI and Tableau dashboards for financial services stakeholders
- Mentored junior developers through code reviews and pair programming
FeaturedProjects
A selection of production AI systems and research projects.
VabGenRx — Clinical Drug Safety Platform
Production-ready multi-agent clinical decision system using Microsoft Agent Framework on Azure AI Foundry. Five specialized agents for safety analysis, contraindication evaluation, dosing analysis, and multilingual patient counselling. Generates comprehensive medication safety reports in under 90 seconds. HIPAA-compliant with 100+ language support and 100% evaluation pass rate.
AI Semantic Recommendation Engine
Production-grade recommendation system processing 6.7M Amazon reviews across 31,100 products. Achieves 85.4% NDCG@10 using hybrid retrieval — BM25 + dense BGE embeddings + cross-encoder reranker — with sub-1s latency. Deployed on GCP with Qdrant Cloud vector DB.
RAG Financial Analysis Chatbot
Production RAG system for financial Q&A over 6.7M historical stock prices and news articles using LlamaIndex, LangChain and Google Vertex AI embeddings. Full CI/CD with DVC versioning, Docker orchestration, and Slack alerting.
Skills&Technologies
The tools I use to build intelligent systems.
Generative AI & LLM
ML & Deep Learning
Search & Retrieval
Cloud & MLOps
Data Engineering
Languages & Tools
Achievements
🏆 2nd Place — InterSystems Challenge, HSIL Hackathon 2026
Secured 2nd place in the InterSystems Challenge at the HSIL Hackathon 2026 — a global health innovation event hosted at Harvard T.H. Chan School of Public Health — by building VabGenRx, an intelligent multi-agent AI solution for clinical drug safety.
Verified Badge↗ CredlyCertifications
AWS Certified Cloud Practitioner (CLF-C02)
Amazon Web Services
OCI 2025 Certified Generative AI Professional
Oracle University
OCI 2025 Certified AI Foundations Associate
Oracle University
Let's Build Together
I'm open to AI/ML engineering roles, research collaborations, and interesting projects. Let's connect.