Avi Fenesh

About

I'm Avi Fenesh. I run tiyuvta, a research lab that helps companies choose, adapt and deploy open models on their own hardware or cloud account. I'm also a systems software engineer at AWS ElastiCache.

At tiyuvta the work is model and hardware assessment, deployment and serving-engine optimization, fine-tuning and evaluation, and cloud setup. We compare options on the customer's workload and budget, then agree the deliverables, handover and support. The lab's research in model execution, quantization, pruning, speculative decoding and Hebrew models feeds that work.

I came to research through implementation: reproduce the baseline, find the assumption nobody checked, train the missing comparison, and let the result change the plan. That is why every study on this site states its protocol and keeps its failed arms. A claim needs a matched baseline, saved artifacts and an honest noise floor.

Before inference work I spent years on datastores, language clients, queues, retrieval and developer tools. I maintain Valkey GLIDE, the official multi-language Valkey client, started valkey-skills, and contribute to Valkey itself. A good part of my open-source time goes to the people around it: the clients team, talks, and helping the people who run it.

I also mentor with Yotzim LaShinui, helping a junior developer from a formerly ultra-Orthodox background find their way into software.

Contact

Email is the fastest way to reach me: aviarchi1994@gmail.com . For a deployment or fine-tuning project, start at tiyuvta.ai/services. Counterexamples to anything on this site are welcome.

Elsewhere

Talks