"I play with code, but more often with ideas."
I am a Product & Technology Leader, entrepreneur, and startup advisor. I specialize in translating complex technology into product strategy, guiding organizations through AI & Data transformations, and advising early-stage startups.
While my day-to-day focus is on product leadership and strategy, I remain a builder at heartโfrequently experimenting with new technologies and ideas.
| Category | Skills & Technologies |
|---|---|
| Strategy & Leadership | PM Strategy โข Startup Advisory โข Data Product Management โข Experimentation |
| Data & AI/ML | Python โข LLMs โข Graph Databases โข Agentic Workflows |
- PLAM: A local-first, multi-agent system designed to orchestrate local LLMs (via llama.cpp), manage hierarchical agents with complex memory systems (pgvector & JSONB), and safely run LLM-generated code inside Docker sandboxes. Optimized for CUDA acceleration on NVIDIA DGX Spark.
- Portfolio Manager: A simple script to manage my retirements accounts on Public.com
- Apache Superset (Contributor): Contributed to the data exploration, time-series, and database connectivity components of this leading open-source data visualization platform.
- python-cayley: An open-source Python client library designed to interface seamlessly with the Cayley graph database.
- Oscar2015-Dataflow: A Google Cloud Dataflow pipeline built in Python to process and analyze Oscar-related tweets in real-time.
Rebuilding Silos with AI
Seeing "Must support MCP" become a standard vendor selection criterion feels like a collective misstep. I understand why teams do it. But asking for MCP instead of an actual capability misses the point. At its core, MCP is just a standardized way to wrap an API for an LLM to consume. A skill running via CLI can often achieve the exact same read/write outcome more effectively.
AI, Authorship, and Education
Every other post on my feed this week is reacting to Claudeโs text watermarking. Except... Google has been doing statistical watermarking with SynthID for nearly two years.
The real anxiety behind the watermarking debate isn't technical. Itโs an existential panic over ๐ฎ๐๐๐ต๐ผ๐ฟ๐๐ต๐ถ๐ฝ.
Gym hacked by AI or lack of product thinking?
The entire tech world lost its mind over an AI agent "hacking" a gym.
The narrative: Claude went rogue, reverse-engineered an API, and deleted a real personโs reservation.
The reality isnโt an AI safety breakthrough. Itโs what happens when we unleash raw technology without product thinking.
The great irony? The person prompting the agent wasn't an everyday consumer. He works for a consultancy advising companies on AI.
๐ Read all writings on LinkedIn โ
A long time ago, in university, I conducted research on cryptography. I still bring that same curious mindset to my daily work.
- ForwardDiffSig: Co-author of The ForwardDiffSig scheme for multicast authentication, published in the IEEE/ACM Transactions on Networking, focused on secure and efficient multicast network authentication.
- Merkle Trees: Co-author of On the Performance and Use of a Space-Efficient Merkle Tree Traversal Algorithm in Real-Time Applications for Wireless and Sensor Networks, published in the IEEE International Conference on Wireless and Mobile Networking and Communications, focused on optimal techniques to traverse Merkle Trees.
- Forward Secure Signatures: Co-author of An Optimized Double Cache Technique for Efficient Use of Forward-secure Signature Schemes, published in the PDP2008: 16th Euromicro Conference on Parallel, Distributed and Network-Based Processing, focused on making Signature Schemes with Forward Security usable. Forward Security is the property by which the signature remains valid even if the private key gets compromised.
