AI Assistant Communications: Architected the omni-channel communications infrastructure powering the AI assistant — voice calls, multi-channel messaging (Slack, Microsoft Teams, Discord, WhatsApp), emails, and in-app chat/calls — integrating Twilio, LiveKit, platform bot frameworks and third-party APIs.

Live Meeting Attendance: Built the assistant's ability to join Google Meet and Microsoft Teams calls as a real participant — participant tracking, two-way screenshare, in-meeting chat and auto-leave — via a Recall.ai bridge.

Voice Identity & Call Recording: Built speaker diarization with voice-fingerprint labelling, splitting co-located speakers sharing a single microphone through per-utterance embedding clustering, alongside call recording/egress and speech-aligned transcripts with in-app playback.

AI Desktop & Browser Control: Built a vision-based (VLM) computer-use agent that automates tasks across remote Ubuntu, Windows and macOS desktops, with CLI-installable clients for connecting a user's own machine.

Organisation Support: Built multi-tenant organisation features on top of personal workspaces — member management and invites, role-based access control with custom roles, ownership transfer, and project/resource sharing.

Integrations: Designed a reusable OAuth integration framework and connectors with per-assistant connect/disconnect flows.

LLM Interface: Built the in-browser developer environment — terminal (streaming output, scrollback, tab-completion), code editor with live execution, and a persistent CodeSandbox-backed file system with Google Drive sync.

End-to-end model development and deployment, such as data analysis, model training, hyperparameters tuning, model selection and cloud deployment on Azure.

Worked with linear models, trees, random forest, XG boost and light gradient boosting machine (LGBM).

Pipeline External Corrosion: ML. Built pipeline external corrosion depth & length prediction models of >90% accuracy.

Pipeline Freespan Formulation: ML. Built subsea pipeline height & length prediction models of >70% accuracy.

HIP: Computer Vision. Worked on working person detection through object detection with YOLO, pose estimation and vLLM with GPT4o. Involved prompt engineering for better inference performance.

Ivy ML Models: Applied Lead. Led the team to expand ML model collection from scratch to 15+ within 4 months, including computer vision and NLP base models for business showcase.

Ivy Transpiler: Introduced the native compilation feature for optimising performance of ML models.

Model Hub: Full stack. Responsible in building client applications and API key authentication.

Console Application: Cloud. Involved in v0 development and API gateway authorisation.

Ivy Framework: Software Engineering. Unified PyTorch, Tensorflow, JAX and NumPy functions, making them easily accessible through a single library. All codes are also readily compatible with the native libraries.

QnA Chatbot for Clinical Tabular Data: ML systems engineering. Full stack development.

Developed TAPAS RESTful endpoints with database and interface for lab report analysis.

Frontend development. Implemented the technology website and generalised a template.