daemonworks.dev
Autonomous systems · built & operated

I build autonomous AI systems—
and keep them running.

Solo, senior, fast. Twenty-six years shipping software. Today I design, deploy, and operate live multi-agent systems that work while you sleep.

Start a project → See the work
↓ Download the capabilities deck (PDF)
Systems in production now · One engineer, not an agency
daemonworks — process monitor
$ systemctl status --fleet
orchestration-engine multi-agent · self-healing · 24/7 running
market-execution live data · real capital · risk-gated running
data-acquisition browser fleet · millions of records running
observability metrics · alerts · auto-recovery running
4 units · 0 faileduptime: nominal
What I build
01

Multi-agent orchestration

Fleets of specialized agents that research, decide, and act — coordinated over a shared data layer, with self-healing, judgment checks, and humans in the loop where it counts.

02

Live execution infrastructure

Real-time systems that run on live data and real stakes: low-latency pipelines, model serving, and hard risk controls that fail safe instead of loud.

03

Resilient data acquisition

Browser-automation fleets and pipelines that gather data at scale and keep running through the rate-limits, defenses, and outages that stop everyone else.

04

Build → operate, end to end

I don't hand you a repo and disappear. I stand the system up, wire the observability, and run it in production — so it actually keeps working.

Selected work

Systems I built and still operate.

Each of these runs in production today. Details are generalized to protect client confidentiality.

01
Multi-agent platform

A B2B outreach platform run by autonomous agents

operating in production

Manual prospecting doesn't scale and hiring a team is slow. I built a platform where dozens of specialized agents — discovery, enrichment, message generation, reply handling — cooperate over a shared CRM and a self-hosted LLM layer. It runs 24/7 across multiple machines, heals itself when a node dies, and stays inside strict spend and quality guardrails. I designed it, shipped it, and I operate it.

Pythonmulti-agent orchestrationself-hosted LLMsMySQL / Postgresbrowser automation
02
Live execution infra

Autonomous trading & market infrastructure

operating in production

Trading fast markets without a desk of people means the machine has to be trusted with real money. I built an end-to-end system that ingests live market data, runs models, and places real-capital orders under hard, automated risk limits. Self-healing data feeds keep it alive through provider outages, and every decision is logged and calibrated. It runs live, unattended.

Pythonreal-time dataQuestDB / Postgresexchange APIsrisk engine
03
Data at scale

Anti-fragile data acquisition

operating in production

The data worth having sits behind defenses, rate limits, and constant change. I built a distributed browser-automation fleet with human-like interaction and self-recovery that harvests millions of records reliably — routing around blocks, retrying intelligently, and de-duplicating on the way into a clean pipeline. Built to run continuously with minimal babysitting.

Pythonheadful automationproxy orchestrationdedup pipelinesscheduling
How I work

One senior engineer. Build and run.

Most automation dies after handoff. I stay on the system, so it keeps earning its keep.

01

Scope

A short, direct conversation to find the highest-leverage thing to automate — and whether it's actually worth building.

02

Build

I ship a working system fast, in production-grade code, with observability wired in from day one.

03

Operate

I run it — monitoring, healing, and improving it on a retainer — so it stays reliable as the world around it changes.

Get in touch

Tell me what you're trying to automate.

If it can run without a human, I can probably build it — and keep it running. Send a couple of lines about the problem and I'll reply personally.

→ andrei@daemonworks.dev