Engineer building real-time sensor-intelligence and edge-AI systems: an SDR/RF intelligence platform (HackRF/Airspy capture → real-time DSP demod → GPU Whisper STT → searchable archive), a wearable ISR computer-vision pipeline (multi-face recognition + custom-trained ONNX demographic models at 30fps), and a 30B-parameter MoE LLM deployed 100% on an iGPU with zero cloud dependency. Australian citizen, no sponsorship required, clearance-eligible. Comfortable across the full stack — from DSP and signal capture through to ML inference on constrained hardware.
Technical Skills
Languages
Python (primary) · JavaScript / TypeScript · SQL · Kotlin / Java (Android) · Familiarity with C / C++ and Go
MediaPipe-based gesture / hand / face tracking pipelines · Servo control (FEETECH ST-3215-C047) on InMoov i2 robotic hand · SO-ARM101 robot arm with MuJoCo simulation + imitation learning · 3D printing for drones, cinewhoops, payload grabbers, perching legs
Multi-layer software-defined-radio intelligence stack: captures RF across UHF/VHF/HF/marine/aviation bands, demodulates in real time (WFM/NFM/AM/SSB), transcribes voice traffic with faster-whisper on AMD ROCm, extracts entities (callsigns, locations) and archives everything into a searchable SQLite/FTS5 database. The DSP core was extracted into a standalone library (rfai-dsp) with anti-alias decimation, phase-continuous VFO mixing and an abstract SDR backend.
Real-time computer-vision pipeline for smart-glasses use cases: MediaPipe Face Mesh (468 landmarks), ArcFace recognition, multi-face tracking at 30fps with a persistent identity library — all in-browser. Ships custom-trained 'Folkus' demographic models (2.3 MB INT8 ONNX, running via ONNX Runtime Web) that beat commercial APIs: gender 92.1%, age 5.37y MAE, ethnicity 72.2% across 7 groups. Camera glasses stream to a host computer that recognises faces and feeds AI context back via phone.
30B-param MoE LLM running 100% on an AMD iGPU — 38 tok/s, zero cloud
Deployed Z.ai's GLM-4.7-Flash (30B-A3B Mixture-of-Experts, Q4_K_M, ~19 GB) entirely on an AMD Radeon 8060S iGPU via ROCm 7.2. The default 198K-context model OOM'd (KV cache alone needed ~53 GiB vs 32 GiB VRAM); solved by engineering a custom 32K-context variant that brings total memory to ~28 GiB for 100% GPU execution with zero CPU offload. Integrated as the offline fallback for local coding agents.
Android BLE scanner with device fingerprinting, GATT explorer and Claude AI analysis
Advanced Android BLE scanner: device fingerprinting, GATT explorer, signal traces over time, behavioural pattern detection (proximity, dwell, repeat encounters), and built-in Claude AI analysis of captured BLE data.
Heart rate, HRV and SpO₂ from a webcam — 100% in-browser rPPG
Browser-based remote photoplethysmography pipeline extracting heart rate, HRV, SpO₂ and stress indicators from regular webcam video. No wearable required — pure signal processing on a noisy real-world input.
Stack: JavaScript · rPPG · Signal processing · Browser ML
Full-stack intelligence pipeline that continuously ingests public message boards, runs NLP for topic clustering, sentiment, authenticity and signal detection, flags narrative spikes via z-score detection, and auto-generates balanced, sourced journalistic articles with SEO/OG metadata. Live dashboard with rolling 24h/7d/30d windows; 5,400+ story artifacts and 14 auto-published articles to date.
On-device voice-AI stack — TTS, STT and round-trip evaluation
Local voice stack for the qalarc AI-OS: TTS, STT, voice-cloning experiments and a round-trip evaluation harness covering radio-protocol-style edge cases.
