ALTER is an Israel-based charity promoting research which improves the long-term trajectory of human civilization.

My research aims at mathematical formalization of general intelligence and value alignment, using tools from computational learning theory and algorithmic information theory. Such mathematical models serve to elucidate the potential failure modes of AGI, clarify confusing conceptual questions, and lead to AI algorithms satisfying theoretical guarantees that imply safety and effectiveness under clear and (ultimately) realistic assumptions.

The Long-Term Future Fund, part of the EA Funds programme of Effective Ventures, provided me with a grant to support my AI alignment research.

Designing and leading the implementation of machine learning algorithms for Cycognito's attack surface mapping system.

Epicycle was an R&D services boutique specializing in computer vision and complex mathematical algorithms.

Metaqube was a start-up developing outdoor Augmented Reality products for mobile devices.

Managing of the software R&D of the company: software and algorithm engineers and a test engineer. The group developed a new software product virtually from scratch. I was fully responsible for the group and personally responsible for software specification. Additionally I operated several subcontractors supplementing the work done inside the company.The product in question is a small form factor 3D scanner based on the company's patented core technology. The software side is a Windows application (WPF GUI, C# high level modules, C++ low level modules) intended for untrained users (consumers) allowing to operate the 3D scanner, run the processing algorithms (3D reconstruction, 3D registration, device calibration etc. - all developed within the group), view, edit and manage the resulting data.

Managing a team of up to 7 people, comprised of algorithm developers and software engineers. The team was a task force which developed the next generation of one of the company's flag software products (A3 LightSpeed), working in a very rigid schedule. The product is a system involving distributed computing, processing of large data volumes and algorithms from the fields of photogrammetry, computer vision and image processing. The team's responsibilities included defining specifications, performing research, designing software architecture, implementing the software and unit testing

Managing a team of 4 algorithm developers. The team was responsible for development of algorithms in the fields of photogrammetry, computer vision and image processing. Most of the algorithms operated inside a distributed computing framework of which I was a coauthor. The algorithms involved math disciplines such as linear algebra, analytic and computational geometry, calculus, numerical analysis, probability theory. The team was responsible for end to end development, from pencil and paper math to tested production code in C++

One of the 1st workers in what was then a start-up. Developing algorithms in the fields of photogrammetry, computer vision and image processing. Many of the algorithms operated inside a distributed computing framework of which I was a coauthor. The algorithms involved math disciplines such as linear algebra, analytic and computational geometry, calculus, numerical analysis, probability theory. The job entailed end to end development, from pencil and paper math to tested production code in C++I worked on a project which received the Israel Defense Prize in 2009