AI-Native Engineer​/Operator; Dev + DevOps

Overview

CHI is an autonomous event-technology company built around a small human team directing more than 100 AI agents. We are hiring the human operator who ships the product, runs the infrastructure behind it, and improves the agent workforce supporting both.

ABOUT CHI

CHI runs the full stack of a live event: ticketing, cashless payments, POS, wristbands, vendor settlements, coupons, CRM, and analytics for festivals, venues, and large-scale events.

When our platform has a bad day, thousands of people cannot buy a drink. That is the level of production responsibility this role involves.

A SMALL TEAM DIRECTING 100+ AI AGENTS

CHI is built as an autonomous company. A small human team directs AI agents that handle repeatable processes across coding, review, releases, QA, on-call support, reconciliation, fraud review, documentation, and operations. Humans set direction, exercise judgment, and define quality. Agents execute. This model is already proven internally, with a much smaller team shipping several times faster than the organization it replaced.

We are hiring a human operator for that agent workforce: an AI-native engineer with strong development and Dev Ops capabilities. This is not a role for someone who occasionally uses AI to generate code. You will build, optimize, and direct agent workflows across product development, testing, debugging, infrastructure, incident analysis, deployment, and documentation. You will work directly with the founder and own real systems, and the agents operating those systems, end to end.

WHAT THIS JOB ACTUALLY LOOKS LIKE

A real week here may include:

• Shipping an organizer-facing feature end to end across the PostgreSQL data model, NestJS API, React backstage interface, tests, and release notes.
• Designing a ticketing or payment flow used by thousands of attendees, from specification to deployment in the app and POS.
• Tracing a failed card payment through the gateway, backend logs, and payment provider dashboard, then shipping the fix and a reconciliation script on the same day.
• Taking a change from pull request to production through a versioned pipeline: conventional commit, automated release, OCI artifact, testing, staging, and production promotion.
• Building an AI agent or CI workflow that reviews pull requests, performs QA, monitors deployments, or drafts release notes and incident reports.
• Responding to a production incident such as a full disk, failed webhook, or missing payment event, restoring the system, back filling the data, and automating the check that catches it next time.

If that list makes you want to open a terminal, keep reading.

OUR STACK

Backend

Node.js, Type Script, NestJS, Bun

Frontend

React, organizer backstage applications, web applications, PWA, and native mobile

Data

PostgreSQL with WAL and PITR, Redis, Kafka, Cassandra, Infrastructure

Docker Compose on dedicated Hetzner VMs, zero-trust networking through Tailscale, hardened hosts, and restricted firewalls

Gateway and identity

KrakenD API gateway, Keycloak, Hashi Corp Vault, agent templates, and App Role authentication

Payments

Stripe Connect, Hyperswitch with PCI vault and cloud KMS, Xendit, Stripe Terminal, and tap-to-pay

Real money. Real settlements.

CI/CD

Git Hub Actions with more than 60 workflows, release-please, OCI configuration artifacts, and gated test-to-staging-to-production promotion

Observability and security

Grafana, Loki, Prometheus, Promtail, Wazuh HIDS, and ClamAV, operating inside PCI DSS scope

AI tooling

Custom coding agents, multi-agent workflows, MCP servers, Paperclip, Hermes agents, LiteLLM proxy, and local or self-hosted LLMs

• You do not need experience with every part of the stack.
• You do need to be the kind of engineer who can understand unfamiliar systems quickly, with AI doing much of the heavy lifting.

THE OPERATOR BAR

At CHI, operator means orchestrating agents instead of doing everything manually.

We expect that you already:

• Ship production code with AI coding agents as your default way of working.
• Design and operate multi-agent workflows for code review, QA, deployment monitoring, incident analysis, and documentation.
• Use AI to debug incidents by providing logs, configurations, stack traces, and system context, then directing the investigation toward the root cause.
• Build automation around AI, including agents, review bots, report generators, internal tools, and repeatable operational workflows.
• Know when AI is wrong. You verify, test, review, and own the output.
• Write documentation and runbooks while working because generating and maintaining them should take minutes, not days.

Your job is not to cover one technical vertical manually.

Your job is to design, ship, and manage the agent workforce that runs it, and step in with judgment where only a human can.

WHAT WE EXPECT

Strong backend engineering skills in Type Script, Node.js, or an equivalent stack, with the willingness to go deep in ours.

• Real Dev Ops experience with Docker, Linux, networking, CI/CD, logs, monitoring, and production troubleshooting.
• Product…