Machine Learning Engineer with experience building AI solutions that improve search, recommendations, automation, and decision-making. Worked on production ML pipelines, LLM and RAG systems, recommendation engines, and computer vision applications. Skilled in Python, PyTorch, TensorFlow, FastAPI, Docker, and MLOps.
I specialize in bringing machine learning models from research to production. My work spans recommendation systems, NLP, computer vision, reinforcement learning, and probabilistic deep learning. Currently pursuing MSc in Artificial Intelligence at THWS while developing ML products at Axinity.
Built an autonomous 5-node LangGraph pipeline that generates institutional-grade equity research reports, covering RAG over SEC 10-K/10-Q filings via Qdrant hybrid search, real-time news sentiment, and a self-correcting Critic Agent with confidence gating, reducing manual research from ~6 hours to ~60 seconds across 6 global exchanges.
Fine-tuned Gemma 2B with LoRA to generate reasoning-based answers from structured data. Multi-source training dataset with 4-bit quantization (bitsandbytes) for inference on consumer hardware.
Fine-tuned ResNet18 for pneumonia detection from chest X-rays with Grad-CAM and LIME explainability. Compressed MobileNetV2 anomaly detector via structured pruning and INT8 quantization — model size reduced from 8.7 MB to 4.4 MB (−49%) with no accuracy loss.
Trained YOLOv8 detector on thermal UAV imagery for automated waterfowl detection. Achieved 86.44% mAP@0.5 and 93.21% Precision on 83 test images with 1,411 ground-truth annotations. Complete end-to-end CV pipeline from preprocessing to evaluation.
Trained and compared multiple RL agents (Q-Learning, Monte Carlo) converging towards the mathematically optimal Blackjack strategy. Results documented in a published technical report.
Built CNN classifier for real-time sign language gesture recognition across 24 gesture classes. Robust preprocessing pipeline with data augmentation for generalisation to unseen hand positions.
Real-time messaging app with bidirectional WebSocket communication, JWT authentication, and end-to-end encryption. Scalable room-based architecture deployed on self-managed Linux server with NGINX.
Optimal Strategy Learning in Blackjack using Deep Reinforcement Learning
Om Borda
2025
This paper explores the application of reinforcement learning algorithms to learn optimal Blackjack playing strategies. We implement and compare Q-learning and Monte Carlo methods, demonstrating convergence to near-optimal play after extensive training episodes.
Designed and deployed a production 4-stage hybrid recommendation system combining LLMs, multilingual embeddings, Qdrant vector search, metadata filtering, and re-ranking
Owned the full retrieval-to-ranking pipeline from feature engineering through offline evaluation and A/B testing
Extended the platform with RAG-inspired semantic retrieval for creator discovery and shipped an OCR-based video analysis pipeline for profiling and content safety
Explored agentic AI workflows as part of ongoing research, covering multi-step LLM pipelines with memory, tool use, and planning.
Supported evaluation of multi-agent systems across task completion and tool-use reliability, working with existing research benchmarks and pipeline tooling.
Built and delivered end-to-end ML and data analytics solutions for client projects, progressing from intern to full-time within 3 months based on project ownership and delivery quality
Full Stack Developer
Greendotslab Software Solutions
May 2022 – Jun 2023 · Gujarat, India
Built and deployed 10+ client web applications end-to-end using Node.js and React, with load balancing and modular architecture for production
