Harsh Shroff
Open to Relocation • AWS ML Certified (Valid through Apr 2028) • Published Researcher
AWS Machine Learning Associate Certified AI/ML Engineer specializing in deploying production LLM systems and scalable ML infrastructure using Amazon Bedrock and SageMaker. Proven expertise in prompt engineering, RAG architectures, and multi-model LLM orchestration with hands-on experience achieving 60% efficiency gains and 92% accuracy in production AI systems.
Latest Updates
AWS ML Certification
Valid through April 2028
AWS Machine Learning Associate Certified with hands-on expertise in production ML systems, SageMaker, and Bedrock deployments.
View CredentialPublished Research
2024
Co-authored "FilletCam AI: Precision color profiling using deep learning" in the Journal of Agriculture and Food Research.
Read PaperProduction Impact
Recent Projects
Delivered production LLM systems achieving 60% efficiency gains and 92% accuracy in real-world deployments.
Core Expertise
Machine Learning & AI
Generative AI, LLMs, RAG, LangChain, PyTorch, TensorFlow, Computer Vision, YOLOv8, OpenCV, NLP, RLHF, Anomaly Detection, Reinforcement Learning, Time Series
Cloud & MLOps
AWS (Bedrock, SageMaker, Lambda, Textract, EC2, S3), MLflow, Weights & Biases, Model Governance, A/B Testing
Software Engineering
Python, C++, Java, SQL, FastAPI, Flask, Git, Docker, Kubernetes, CI/CD, Microservices, Test-Driven Development, API Development
Data Engineering
Pandas, NumPy, Spark, Hadoop, Feature Engineering, Data Pipelines, ETL, PostgreSQL, MongoDB, Redis
Featured Projects
Enterprise Document Intelligence Platform
Built scalable document processing system automating extraction from 2,500+ PDFs using LLM-powered OCR pipelines and cloud infrastructure with real-time API endpoints.
Multi-Modal Recommendation Engine
Engineered hybrid recommendation system combining structured data analysis with computer vision, reducing user bounce rate by 20% through personalized AI-driven recommendations.
AI-Powered Medical Diagnosis System
Designed end-to-end ML web application for medical image classification achieving high diagnostic accuracy using deep learning and computer vision with production-ready inference pipeline.