Research Engineer & ML Scientist
Building intelligent systems with research rigor & engineering precision.
Researcher and ML engineer bridging cutting-edge research and production AI systems. My work spans computer vision, NLP/LLMs, reinforcement learning, agentic AI, and MLOps—from model training to scalable deployment. Grounded in large-scale numerical simulation and scientific computing, I bring engineering rigor to data-driven modeling as a published researcher focused on building deployable intelligence.
Experience
Present
AI/ML Research Intern
- Developed a two-stage RAG system that decomposes report-level prompts into sub-questions, retrieves and deduplicates evidence across multiple embedding-space regions, and synthesizes citation-grounded technical reports using LangChain, ChromaDB, and cross-encoder re-ranking.
- Fine-tuned RF-DETR on a custom SAR image dataset, achieving mAP 0.614 competitive with published literature; diagnosed overfitting via train/val loss divergence and scoped SARDet-100K as the next data-scaling step.
- Built an AI agentic pipeline that converts any research paper PDF into a 15-minute digest, autonomously generating narrative summaries, AI-illustrated diagrams, key tables, and a companion Jupyter notebook.
Dec 2023
Aerodynamics Research Assistant
- Ran 3D CFD simulations on an HPC cluster (SLURM), cutting wall-time by 75% through parallelization; processed and visualized large-scale flow-field datasets using Python and ANSYS CFD-Post.
- Quantified surface roughness effects through wind tunnel experiments and CFD: measured a 5° delay in flow separation and a 16% lift increase, contributing to a co-authored AIAA 2025 publication.
Dec 2020
Finite Element Analyst
- Performed structural and FSI FEA simulations (ANSYS Mechanical) for industrial projects including subbase tanks, car-park brackets, and a floating solar plant under static and dynamic wind load conditions.
Technical Skills
Projects
Customer Churn: End-to-End ML Pipeline
Production ML pipeline for customer churn prediction with model versioning, automated retraining, and inference API using MLflow, FastAPI, and Docker.
OpenFOAM RAG: Citation-Grounded Q&A
Two-stage RAG pipeline that decomposes queries into sub-questions, retrieves from OpenFOAM documentation, and generates citation-grounded answers. Published at RAG4Report Workshop @ ACL 2026.
PaperDigest: Agentic PDF-to-Digest
Agentic system that ingests academic PDFs, extracts structured content, and generates concise digests using FastAPI and Gemini. Automated pipeline from upload to summary with key-finding extraction.
SAR Aircraft Detection (RF-DETR)
Fine-tuned RF-DETR on synthetic aperture radar imagery for aircraft detection. Achieved mAP 0.614, competitive with published benchmarks. Diagnosed overfitting and scoped SARDet-100K for data scaling.
Student Misconception Detection
Fine-tuned Qwen2.5-Math-1.5B-Instruct with Unsloth and a compact MLP classification head to identify student misconceptions in math reasoning. Improved MAP leaderboard from 0.885 to 0.925 (+4.5%).
Stable Video OCR: License Plate Recognition
Real-time detection using fine-tuned YOLO11 + EasyOCR. Eliminated flickering via a majority-voting algorithm over a 12-frame rolling buffer, producing stable text output across video frames.
Video Instance Segmentation: Mask R-CNN
Per-frame object detection and pixel-level segmentation pipeline using PyTorch's pre-trained Mask R-CNN. Renders per-instance colored masks and bounding boxes on live video streams.
Research
Decompose, Retrieve, Cite: A RAG Pipeline for Structured Report Generation from Technical Documentation
Effect of Surface Texture on the Lift and Drag of Small Spinning Balls
Resume
Himanshu Dhurve
AI/ML Engineer & Researcher
Version 6.0 · March 2026Education
M.S. Aerospace Engineering
San Diego State University, USA · GPA 3.52 / 4.0
Recipient, Master's Research Scholarship · 2022
B.Tech Mechanical Engineering
Dr. Babasaheb Ambedkar Technological University, India · GPA 8.57 / 10.0