Senior ML Engineer (December 2022 – Present) – Healthcare AI Sector

• Collaborated with cross-functional teams to improve the performance of the telepathology product; successfully integrated an AI-based auto-diagnosis feature that increased the number of cases diagnosed per day by 30%.
• Developed a cutting-edge semantic segmentation model for predicting urothelial carcinoma in histopathology slides, achieving 90% accuracy and reducing manual annotation labour by 80%.
• Designed and deployed production-grade machine learning models, transitioning AI solutions from notebooks to production-ready systems, ensuring real-time diagnosis and analysis in healthcare environments.
• Published a paper on using Artificial Intelligence for automatic identification of lymphovascular invasion in urothelial carcinomas, presented at an international AI congress.
• Developed an object detection model for identifying bacilli in tuberculosis sputum tissue images, projected to screen at least 200 cases per day with 95% accuracy, reducing manual analysis time by 30%.
• Implemented vision prompting techniques using advanced models, expected to improve diagnostic decision-making time by 50% and enhance clinical consistency in complex cases.

Senior ML Engineer (January 2020 – Present) – HealthTech Sector

• Led the design and development of a machine learning regression model to predict physiological signals from videos with 85% accuracy, contributing to a video-based health monitoring platform with built-in scalability and monitoring.
• Built end-to-end scalable ML pipelines using Kubeflow and AWS for continuous model training, version control, and deployment, reducing time-to-market by 20% and ensuring MLOps best practices.
• Optimized business model by licensing SDKs and scaling the SDK library, generating profitability and increasing revenue by 50%.
• Inventor of US patents for AI-based non-invasive health monitoring, non-contact blood sugar monitoring for diabetes, and respiratory disease detection.
• Refined and optimized Large Language Models (LLMs) with RAG (Retrieval-Augmented Generation) techniques, contributing to a 15% increase in revenue from a mobile health and wellness application.

Artificial Intelligence Engineer (July 2020 – June 2021) – Robotics Sector

• Spearheaded the development of an Explainable-AI and anomaly detection solution using deep learning and computer vision, integrated into manufacturing processes, reducing production defects by 25%.

Machine Learning Engineer (January 2020 – July 2020) – Robotics Sector

• Engineered a factory safety and surveillance AI monitoring software leveraging edge IoT architecture, reducing safety incidents by 40% and saving 700+ man-hours per month.

Intern (August 2019 – October 2019) – AI & Robotics Sector

• Conducted research and developed a proof of concept for using gait analysis and 3D human posture data for early Alzheimer’s detection, achieving 75% accuracy.

Programming:  Python, MATLAB, C++, CUDA< SQL, Docker & JavaScript

ML Frameworks: TensorFlow, PyTorch, OpenCV, ONNX, NVIDIA-MONAI, Spacy, Statsmodels,Scikit-Learn, Stablebaselines3, Scipy, Cytomine API, Bio Python, LangChain, Llamalndex, Autogen, Ray, Apache Spark

ML Ops: NVIDIA Triton Inference Server, TensorRT, AWS Sagemaker, Vertex AI, Kubeflow, Compute Engine, Cloud Storage, Apache Kafka

Deep Learning Technologies:  Segmentation, Object Detection, Reinforcement Learning, Casual Reasoning, Natural Language Processing, Regression Analysis, Responsible SI, AI Governance, AI Safety, BERT, GEMINI, GPT, DALL-E, AlphaFold, BARK, Falcon-13B, Llama-2, LLM (RAG Tuning, DPO)

Tools:  Plotly, Tableau, ImageJ, Docker, GIT, Linux, Build-Root, Databricks, PowerBI

For further information on this candidate please use reference number: 015