mert@arch:~% whoami
Mert Sefa Akgün
mert@arch:~% cat focus.txt
Lead software engineer · AI systems
I design and ship real-time AI agents, voice systems, memory infrastructure, and the observable runtimes underneath them.
No skill bars. No logo cloud. Each entry exposes the constraint, architecture boundary, and evidence lane.
A production-oriented LiveKit pipeline spanning audio ingress, VAD, STT, LLM/tool mediation, TTS, interruption recovery, memory side paths, and stage-level telemetry.
scope: NDA-safe architecture from production work
A typed memory policy where source, trust, sensitivity, allowed use, expiry, and auditability stay attached to retrieval instead of disappearing into embeddings.
scope: Personal agent infrastructure
A field-system design combining UWB ranging, Bluetooth provisioning, and GPS/time sync under access-control hardware constraints.
scope: Embedded/RF systems roots
Radio boundaries · calibration · deployment constraints · hardware notes
open artifact ->Keyboard first. Press / from anywhere to focus; Esc clears query and tag state.
An NDA-safe field note on where voice-agent latency accumulates, which stage owns each delay, and why interruption recovery belongs in the budget.
Why source, trust, sensitivity, allowed use, expiry, and audit gates must remain first-class in an agent memory system.
A compact C++ systems note preserved from the old wiki: why global object initialization order leaks across translation units.
Memory placement as a maker primitive: ownership, lifetime, and why runtime shape matters for C, C++, and Rust.
From the old blog: UWB ranging, local Bluetooth configuration, GPS for outdoor/time sync, and real access-control hardware constraints.
A cleaned-up cryptography primer: define the terms, keep the threat model visible, avoid ceremony.
A preserved algorithm/wiki reference from the old site: universal integer coding using Fibonacci numbers as a compact representation exercise.
A tiny old wiki entry promoted into a craft note: editor variants, workflows, and the personal-tooling lineage behind the site.
Design notes for making autonomous tools feel inspectable: command logs, approval moments, abort buttons, and resumable context.
My work moves from audio frames and constrained devices to agent orchestration, retrieval policy, telemetry, and production operations. I care about explicit ownership, bounded failure modes, and evidence that survives the demo.
Queue boundaries, cancellation, interruption, and recovery are product behavior.
Retrieved context is evidence, not ambient permission to act.
Per-turn traces and percentiles beat a comfortable average.
Bound side effects, expose state, and keep the rollback boring.
mert@arch:~% ./open-thread --topic hard-systems
Real-time AI, voice systems, agent infrastructure, memory, observability, embedded systems, or architecture where the machinery matters.