AI Systems Engineer. From concept to working system.
I conceive, design and build AI-powered systems — connecting models, tools, software and hardware, from the first idea to a working product.
Voice systems at Snips / Sonos. Collaboration prototypes at SAP. Physical interaction research at MIT Media Lab. Today, I bring that experience to local AI, agentic workflows and connected objects.
Selected work
Four systems I conceived and built. Different interfaces, the same concern: make the whole loop work.
Synapse ↗
Voice, multimodal conversation, source-backed research and agent-driven development.
Read the system story →
Pucclab ↗
A physical espresso lab: extraction telemetry, tasting and an evidence-grounded next experiment.
Explore the instrument →
Archivist ↗
Answers grounded in repository files, with visible sources and reviewed changes.
Follow the retrieval loop →
F1 Race Replay ↗
A dedicated race display. Deterministic facts, locally generated editorial chapters.
See the replay →What I bring to a team
I work across the boundaries where a promising demo becomes a usable system: interaction, orchestration, inference, persistent state, embedded hardware and deployment. I can define an experience, make the technical choices and build the pieces that let someone actually use it.
The projects here originate in my own concepts and design work. I take them through implementation and iteration; professional contexts and team contributions are identified where relevant.
Built in different contexts
- Snips / Sonos — voice and product prototyping. Contributed to the product definition and UX specification of Sonos Voice Control. Conceived and built contextual listening prototypes spanning interaction, lyrics retrieval, sensing and ESP32 firmware.
- SAP — collaboration. Conceived the idea, built the prototype and developed the OS X application within the Chairman’s project team. The concept later evolved into CoScreen.
- MIT Media Lab — physical interaction. Created SPrAyCE, a spray-based interface for drawing in mid-air, connecting a physical gesture to digital creation.
- Independent R&D — AI systems. Design, build and operate the local inference, voice services, agent integrations and interfaces behind the projects in this portfolio.
How I build
Start with a use case. Make the whole loop work. Then find the weak boundaries: ambiguous requests, missing context, unavailable services, unsafe actions and outputs that cannot be verified.
I use models where interpretation or generation helps, and explicit software contracts where correctness matters. That can mean a source-backed answer, a reviewed diff, an event ledger or a hardware control loop that keeps working without the model.
My local setup
The local machinery behind my projects. One agent, a routing layer, and dedicated compute for reasoning, perception and voice.
Hermes
Plans, codes & calls tools
Dedicated VM · terminal & workspacesThe right capability
Intent, media assets & service APIs
LLM gateway · stable model endpointSpark cluster
2 × ASUS GX10
NVIDIA GB10
Qwen 3.8
Flash Next
NVFP4 · SGLang · TP2
128 GB unified memory / node
Multimodal node
Workstation
NVIDIA RTX 5090
Qwen3-Omni
30B · A3B
NVFP4 · Thinker
Available when the workstation is free
Speech node
MS03 · MS-02 Ultra
RTX PRO 4000 Blackwell SFF
Qwen3 ASR 1.7B
Qwen3 TTS 1.7B
Transcription · voice synthesis
Independent of the multimodal node