Full StackAI Engineer.
Experience
Contract Full-Stack AI Engineer & Data Scientist
Independent — Multiple Clients
Loredana — AI coaching SaaS: architected a full-stack Next.js + Firebase platform; built 'Sage Journal' with Gemini for sentiment-aware coaching feedback and real-time Recharts dashboards (six-pillar resilience radar, somatic body mapping).
Telleosis / MyJamb — EdTech AI tutor: engineered a FastAPI backend on Cloud Run with a RAG pipeline over BigQuery Vector Search to retrieve lesson contexts; designed SQL gamification and randomised exam generation.
Kotchakorn — language-learning AI: interactive Thai-learning app in Python Shiny + BigQuery with Gemini 2.5 Flash streaming proficiency-tuned lessons; automated PDF and flashcard generation.
GoChurch — community AI agent: Next.js app with a custom domain-specific agent grounded in theological texts (KJV) and blog content for accurate, context-aware answers.
Lead Data Scientist
Gifftid Ltd.
Architected and shipped the complete GenAI platform — GCP infrastructure, CI/CD for ML, containerised Docker / Kubernetes deployments, monitoring, access controls, chatbots, vector databases and analytics dashboards.
Partnered with the CEO on strategic AI direction; identified market gaps and shipped SME-focused tooling.
Positioned Gifftid as a leading AI-driven platform for small and medium enterprises.
Data Scientist & Software Engineer
The Hut Group (THG)
Built production GPT chatbots grounded to company data with hallucination prevention, moderation guardrails, RAG and chain / tree-of-thought prompting (LangChain, NVIDIA NeMo Guardrails).
Shipped multi-modal vision-language outfit recommendation chatbots using InstructBLIP and GPT models on Azure; deployed AI serving 7M+ monthly users.
Built topic detection and sentiment-analysis pipelines using guided LDA, RoBERTa, BERT and DistilBERT, integrated into production APIs.
Featured at the THG Ingenuity Future of Commerce 2023 Industry Innovators Conference; trained and project-led other data scientists.
Earlier Research Roles
St Andrews · Trinity College Dublin · Maynooth · Augary (US) · DFKI (Germany)
ML on 2,500 Full-HD videos across a 12-node cluster for video-encoding optimisation.
ROS / TurtleBot 3D room-change detection extending MIT's Kintinuous SLAM.
Real-time on-device lane detection — patent-pending and IEEE-published; spatial 5.1 audio research with Google & SFI Ireland.
Core Stack
Published Apps
Andhera
A minimal dark video & audio player — drag a file, it plays. No ads, no telemetry.
Naqsh
A small, opinionated designer's terminal emulator — quiet typography, native binary.
Spectra
A terminal music visualiser for macOS — taps system audio into a live spectrum.
Mist
A technical-brutalist native macOS IDE — full git, LSP and terminal engine, zero Electron weight.
Aks
A GPU-accelerated photo editor & Instagram story maker for macOS — fast, native, offline.
Saya
A keyboard-first zen browser for macOS — quiet, distraction-free, native.
Education
MSc Dependable Software Systems (DESEM)
University of St Andrews (UK) & Maynooth University (Ireland)
2016 — 2018
Erasmus Mundus Scholarship. Thesis: 3D room-change detection on a TurtleBot with an RGBD sensor, extending MIT & Maynooth's Kintinuous visual SLAM — 83% (2D) / 100% (3D) accuracy.
Certifications
Awards & Recognition
Languages
Patents & Publications
Real-Time Lane Departure Warning System on a Lower-Resource Platform
US PATENT PENDING · IEEE PUBLICATION
Real-time lane detection and tracking on commodity Android hardware. Computer-vision pipeline in Python with CPU-intensive routines in C++ via ctypes, ported to Java for Android deployment. Extensively validated against the Caltech-Lanes dataset.
© Ibrar Yunus 2026