Selected engineering work
Project
Verified active years: 2026
Worked with client technology leaders and finance teams to understand financial metrics and calculation methods, then translated that knowledge into SAP-connected Python tools for AI agents. A separate fictional demo illustrates these concepts.
My role: Client-facing AI & backend engineer
Project
Verified active years: 2026
Business-process recordings become documentation, BPMN diagrams, test cases and a searchable knowledge base — semantic embedding with pgvector, hybrid vector + governed SQL retrieval, async job orchestration.
My role: Core AI and backend engineer
Project
Verified active years: 2024, 2025, 2026
Multi-camera product recognition on YOLOv7/v9 with TensorRT — sub-200 ms responses at 15–20 FPS, hot-reload model serving, end-to-end CI/CD.
My role: AI / ML systems engineer
Project
Verified active years: 2025
A framework that transforms unstructured production logs into structured insight for root-cause analysis, combining fuzzy clustering, ReAct-based LangChain agents and locally hosted LLaMA models. Brought log investigation down from hours to seconds and streamlined over a thousand review cycles through SME automation.
My role: AI / ML systems engineer
Project
Verified active years: 2025
High-performance ML-serving APIs for real-time shelf mapping, built on Flask and Gunicorn and integrated with Azure Event Hubs and MongoDB. Engineered hot-reload capability so models update without downtime, plus monitoring, structured logging, automated scalability and fully containerised deployment.
My role: AI / ML systems engineer
Project
Verified active years: 2024
FastestDet architecture refined for a 35% accuracy gain; real-time detection deployed on Renesas MCUs and Sony IMX500 smart cameras — AI where there is no cloud to fall back on.
My role: AI / ML systems engineer
Project
Published in portfolio:
An experimental vision project exploring age-range estimation and anatomical segmentation from chest X-rays.
My role: AI developer
Project
Published in portfolio:
An image-processing prototype for outlining and counting regions in dental X-rays using Python and OpenCV.
My role: AI developer
Project
Verified active years: 2024
Helped develop a reusable enterprise vision-inspection suite from scratch through deployment, turning client ideas into inspection workflows and reviewable results with cross-functional teams.
My role: Hands-on application and computer-vision engineering
Project
Published in portfolio:
A visual-inspection demonstration for packaging, including object counting and checks for label and product discrepancies.
My role: Prototype developer
Project
Published in portfolio:
A recommendation proof of concept using product information, reviews and video transcripts to support paddle selection.
My role: AI developer
Project
Published in portfolio:
Computer vision for identifying solar-panel defects, accompanied by a credited article about the inspection workflow.
My role: AI developer and article author
Project
Published in portfolio:
A Stable Diffusion exploration for visual concepts, with a public Colab notebook that wraps Hugging Face custom-diffusion training in Streamlit.
My role: Prototype developer
Project
Published in portfolio:
A workout-monitoring demonstration exploring body tracking in exercise video with Ultralytics YOLOv8.
My role: Prototype developer
Project
Published in portfolio:
A Streamlit prototype that retrieves YouTube transcripts, splits the text and generates summaries using LangChain and GPT-3.5.
My role: Prototype adaptation
Project
Verified active years: 2023
Custom object-detection and segmentation models built and optimised for embedded devices, tuned for on-device speed and accuracy, with real-time detection deployed on IMX500 intelligent vision sensors. Transfer-learning workflows cut training time and integration effort substantially.
My role: AI / ML systems engineer
Project
Undated / awaiting review
Domain-specific question-answering systems and custom neural networks accelerating early defect detection across railway, telecom and solar industries. Alongside these, end-to-end GenAI builds including Stable Diffusion–based text-to-image models, LLM-powered analytics pipelines, and vector-database retrieval systems using LangChain with custom prompt-engineering frameworks — plus fine-tuning work across Falcon, LLaMA-2 and BERT-family models with PEFT.
My role: AI / ML systems engineer
No projects match this year.