№ 8817@serhan
Serhan Yilmaz
yılmaz means perseverant in turkish. i tend to live up to it.
currently building
magnos — the ai operating system for financial intelligence. agentic palantir × mckinsey for finance.
asking for
people replacing entrenched saas with ai-native systems. anyone thinking hard about agent loops, compound ai, and evals at scale. ICLR/NeurIPS folks coming through SF.
offering
if you're shipping multi-agent systems in production — i've shipped four, broken most. happy to compare notes on what worked and what was a trap. also: anything turn-taking / voice-ai / streaming inference (built streamingVAP on Furhat humanoid robots at KTH).
shipped — on file
- ·01co-authored INCLUDE — ICLR 2025 Spotlight (multilingual eval, 44 langs, 197K QA)
- ·02founded kAi Sabancı (600+ members, NVIDIA Student Network founding cohort, first outside the US)
- ·03EPFL Project Charisius — 2200% perf gain on gradient aggregators, 96% runtime reduction
- ·04KTH StreamingVAP — 93% turn-taking accuracy on Furhat humanoid robots
- ·05CMU CASCADES — >60% over-baseline question generation
links