The story
Twenty years, three acts
Every engineer's career is a story about what they were trusted with. Mine runs from the trading floor of a global bank, to the front door of a new financial world, to a rack of machines that answer questions with sources. The thread underneath it has its own page.
- Act I · Systems that are not allowed to fail
-
Origins
San Juan → Cornell
The question that runs the career
Puerto Rico, before cloud anything: if you wanted a computer that worked, somebody had to build it - and by fourteen, people were paying me to be that somebody. At Cornell I found the discipline built around my favorite question. Information science asks: how do you represent the real world inside a computer? Twenty years later, I am still answering it - at larger and larger scale.
-
Engineering
Goldman Sachs · summers 2010 - 2012
Trust you earn by shipping
The same trade-processing team took me back three summers running. I built the tools that check the firm's records against its own risk systems, and ran the mentoring program for the incoming interns while still being one. Teaching the next class while shipping for this one: a pattern that never stopped.
-
Engineering
The floor · 2013 - 2015
Where correctness is the whole job
Securities technology: the systems that double-check the firm's trades and file the reports the law requires. When your software sits between a bank and its regulators, correctness is not a virtue - it is the whole job. I built a query service shared firm-wide as internal open source, in the firm's own in-house language. And I helped stand up a round-the-clock operation, spanning dozens of teams, that catches errors before they become anyone's worst day.
- Act II · The leap, and the years in command
-
June 2015
Two names, one month
I left the “perfect job” and incorporated two companies in the same month: LazoffTech for client engineering, and a second for the long research project underneath. The first has funded the second ever since. The client years taught the lesson every senior engineer eventually learns. Organizing the material is harder than writing the code - and the structure you choose for knowledge determines everything you can do with it later.
-
September 2016
A list called “Websites to make”
One year into independence, I wrote myself a five-line plan. The first line was this website - “the main site where all the projects are listed.” Most of that list is now real. The first line is the page you are reading.
-
Engineering
ConsenSys · 2018 - 2024
The front door to a new financial world
I joined through the education arm, building the platform that taught developers an entirely new way to program. I rose to senior engineering manager, responsible for every website behind MetaMask and consensys.io - the pages millions of people walked through to enter an economy that had not existed a decade earlier. Running the web presence of software that guards people's money teaches you a professional level of paranoia. I recommend it.
-
Engineering
Chainlink · 2021 - 2024
The company whose product is an oracle
Chainlink builds the systems that tell blockchains the truth about the outside world - prices, events, facts. The industry's own name for them: oracles. I built the sites and tools its developers rely on - three of those years while still running the web at ConsenSys, both engagements flowing through the research company. My day job was helping machines report facts with sources. So, it turned out, was everything else.
- Act III · The machines arrive
-
Engineering
2023
A machine in the house
Everything the career taught - connecting information, making it findable, running systems that do not lose things - pointed at one place, and it was not a data center. It was a machine on my own shelf, running models I could open up and inspect, holding data that never leaves the building. I stopped renting my computing and started owning it.
-
The rule that runs through everything
An answer arrives with the source it came from - or it does not arrive.
I found the rule on the oldest shelf in the world, and I wrote it into the code.
-
Engineering
2026
The year of the machines
When the AI tools matured, two decades of collecting became fuel. In one year I shipped more new projects than in every earlier year combined: knowledge graphs, honest evaluations, tireless helpers, and an entire fleet of teaching sites. All of it built and run by one person, with a rack of GPUs at home. What every engineer dreamed of - one person building like a team - finally exists. It rewards exactly the people who spent years preparing for it.
-
Research
Now
The room where the voices answer
The strangest thing I have ever built: I turned the oldest library I know into a knowledge graph, every piece carrying its source, every author joined to their teachers. Then I taught a machine to answer the honest way - name where you read it, or say nothing. Eight voices now answer from that graph, out loud, from a machine in my house, and anyone can talk to them. It is my grounding testbed: the hardest citation problem I could find, running in public.
-
The rule, measured
Does the rule hold?
It holds. Every answer must name a real source you can go and look up, verified word for word against the actual text - and if no source exists, the system says nothing. Only a model that clears every check ships.
That discipline - cite or stay silent, measured, in public - is what I want to bring to a team working on AI you have to be able to trust. The research behind it is at jew.tech; the productized version is Digital Twin Pro.