Building agents for silicon intelligence
Building agents for silicon intelligence. Founder of Simra, an EDA orchestrator for analog and mixed-signal teams.
I spent years doing analog and mixed-signal chip work the hard way: schematics, layout, simulation, post-layout debug, tapeout pressure, and the small judgement calls that never fit cleanly into a textbook. Simra is the tool I wanted during those loops.
The current focus is simple: help semiconductor teams reuse proven IP faster without asking them to abandon Cadence, Synopsys, Siemens, Keysight, open-source flows, or the review gates they already trust. Simra sits beside the existing toolchain, runs the repetitive work, captures evidence, and brings engineers back in when judgement matters.
Before Simra I explored data ownership, crypto, agents, and consumer products. A lot of that was useful training, but the real pull was back to chip design: a difficult, high-trust field where better software can save expert engineers from endless manual glue work.
EDA orchestration for analog and mixed-signal teams: existing tools, private environments, repeatable evidence, and engineer signoff.
IMTEK, University of Freiburg. Multidisciplinary systems engineering across mechanical, fluidic, and electrical domains, with a focus on circuit and system design.
PhD work at TU Berlin with multiple tapeouts, including 22 nm FDSOI high-speed Ethernet PHY circuits and 180 nm energy-harvesting work.
Taught electromagnetism, then built Datalatte and survey/data experiments. The useful lesson: start from a painful workflow, not from an ideology about technology.
Used hackathons as fast product reps around privacy, data, social graphs, and agents. The through-line was learning how to ship quickly and test ideas with real users.
I am focused on Simra right now. Reach out if you work on analog, mixed-signal, EDA workflows, silicon IP reuse, or if you want to compare notes on building useful AI agents for hard engineering domains.