Skip to content

Staff Software Engineer · AI Infrastructure

I build production infrastructure for AI agents, and operate all of it myself.

Memory, code intelligence, and real-time messaging: three live products on one 4-core ARM box, running 24/7. Built by one person, operated by the same person, shipping since 2011.

Selected results

1830×
Graph hot path, cut from 446ms to 0.24ms.
go-code · krolik.tools
72.5%
LoCoMo memory benchmark, ahead of Mem0's open baseline.
MemDB · memdb.ai
99.6%
Message delivery at 5,000 users per room, load test.
OxPulse · oxpulse.chat

By the numbers

3
Live products: memdb.ai, krolik.tools, oxpulse.chat
35
MCP tools in go-code across 16 languages
39+
Live containers on a 4-core ARM box, 24/7
14
Years shipping production since 2011 · 1,743 commits in May 2026

Live products

What I've shipped

Three production systems. Own domains. Open in a new tab.

01

MemDB · memdb.ai

Self-hosted long-term memory database for AI agents. Pure Go core, zero Python in hot path. Single docker-compose: PostgreSQL + Apache AGE + pgvector + Qdrant + Redis + embed-server. 72.5% LoCoMo LLM-Judge, beating Mem0 by 5.62pp using open-source primitives only. Apache 2.0, v0.23.0 in production, Discord community of early adopters. GoPostgreSQLApache AGEpgvectorQdrantRedis

02

go-code · krolik.tools

Code intelligence MCP server for AI coding agents. 35 tools across 16 languages: semantic search, call-graph and dataflow analysis, automated PR review. Apache AGE knowledge graph + pgvector + ColBERT reranker. Bridges Prometheus alerts and Jaeger traces directly to file:function hypotheses. Gotree-sitterApache AGEpgvectorColBERTPrometheusJaegerMCP

03

OxPulse Chat · oxpulse.chat

Censorship-resistant encrypted chat and real-time video, usable down to 1 KB/s. Verified a 5,000-user-per-room broadcast at 99.6% delivery (load test) on a 4-core box. Multi-domain partner-edge architecture (oxpulse.chat + 4 partner brands). Rust backend, SolidJS widget, production CSP. RustAxumSolidJSPostgreSQLWebRTC

Engineering & infrastructure

What makes it run

Libraries, orchestration, observability, built by the same hands.

  • oxpulse-sfu-kit · Reusable WebRTC SFU library on str0m. Simulcast, dual BWE (Kalman + googcc), pacer, AV1-DD, active speaker. Published v0.11.0 on crates.io. Ruststr0mTokioWebRTC
  • Multi-MCP ecosystem · 8 additional production Go MCP servers: web research, job hunting, startup research, security probing, knowledge graph, web automation, WordPress automation. All healthy 24/7. GoMCPDockerPrometheus
  • dozor · Auto-deploy orchestrator for a 24-host fleet. GitHub webhook → debounced build queue → systemd. Telegram bus for alerts. GoDockersystemd
  • Observability stack · Prometheus + Loki + Jaeger + Grafana + Alertmanager + 4 exporters. Hand-wired docker-compose. PrometheusLokiJaegerOTLP

Why now

Choosing an IC seat, on purpose

For 14 years I ran my own products and carried production myself: on call, no team to escalate to, every outage mine to fix. That taught me what holds up under real load and what only looks good in a demo.

I'm choosing an individual-contributor role deliberately. I want to go deep on hard infrastructure problems alongside a strong team, not manage one. I ship, I operate, and I take the pager. The ownership instinct stays the same; only the org chart changes.

Open to

What I'm looking for

Staff+ engineering roles at AI infrastructure companies

Anthropic, Cursor, Sourcegraph, Cognition, and similar: code intelligence, agent memory, distributed systems, platform, internal tooling. 14 years of carrying production pain personally means I ship and operate, not just prototype.

Founding-engineer roles at early-stage AI startups

AI-infrastructure and developer tools, where deep ownership and 0-to-1 building matter. Same work, earlier stage.

Let's talk

Staff and Senior engineering roles at AI-infrastructure and dev-tools companies: code intelligence, agent memory, distributed systems, platform. Open to founding-engineer roles at early-stage startups too. SF Bay Area, onsite or hybrid.

Email →
Available now
location Bay Area · UTC-7
prefer remote, SF hybrid OK