A&W
Summary
🤩
RockstarAlex W is an Open Source Developer and AI Software Engineer with 8 years of experience building production ML and cloud systems from edge devices to AWS backends. He architects on-device Core ML solutions (notably contributing core features to FluidAudio, an iOS/macOS audio AI framework with 1k+ stars) and has delivered highly optimized multilingual CoreML ASR and speaker diarization achieving massive real-time speedups and broad adoption. At Varicent he built GenAI integrations, RAG/agent pipelines, and led cost-saving cloud migrations and database optimizations that cut operational costs substantially. Comfortable across Python, TypeScript, Terraform, and SIMD optimizations, he bridges model conversion/quantization work for on-device deployment with scalable server-side automation. Based in Canada, Alex combines hands-on open-source impact with pragmatic engineering that turns research models into efficient, user-facing products.
8 years of coding experience
Github Skills (84)
speaker-identification10
text-to-speech10
automatic-speech-recognition10
parakeet10
apple-silicon10
audio10
avfoundation10
swift10
nvidia10
voice-activity-detection10
speaker-recognition10
macos10
ane10
speaker-diarization10
objective-c10
Programming languages (9)
Github contributions (5)
Alex-Wengg/leetcode
Jun 2021 - Nov 2023
Contributions:941 pushes in 2 years 5 months
FluidInference/FluidAudio
Jun 2025 - Jul 2026
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Contributions:10 releases, 235 reviews, 124 PRs in 1 year
audiocoremlspeaker-diarizationspeech-to-textswift
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.