We're building an autonomous, self-learning AI SRE - an agent that supercharges engineering teams to investigate production incidents 10X faster than they could manually. It reads logs, correlates metrics, reasons through hypotheses, and tells you what's actually wrong. It's in production at high-scale companies, hitting 78%+ accuracy on real production issues.
Our users love it. Now we want to cement Cleric as the first responder engineers rely on when things go wrong.
Define what an AI SRE should be
AI SRE is the next hard challenge after coding agents. There's no playbook. Examples of questions we'd like you to own:
When AI handles the reasoning, how do engineers stay sharp for cases it can't?
How do you build trust when someone needs to verify agent conclusions at 2AM?
You'll help answer these by talking to engineers, running product experiments, and shaping how Cleric approaches problems.
This is a Staff-level role. You'll work directly with the founders to set product direction. You'll have real technical autonomy: architectural decisions, system design, and the latitude to fix things you think are broken.
Build the systems that power investigations: data flows, integration points, how agent reasoning surfaces to engineers
Work directly with engineers: calls, war rooms, watching them debug live systems - and turn that into product direction
Define what "good" looks like for investigations. Identify gaps. Work with AI engineers to close them.
Run experiments: try new ways of surfacing results, measure engineer trust, double down or delete based on signal
Make technical calls across the stack (Python, integrations, frontend when needed) with the ownership to see them through
Set engineering standards that let us ship fast and maintain quality
You are
An engineer who's owned products end-to-end - not built to spec, but decided what to build. You can point to specific features and explain why they worked.
Familiar with production pain: you've carried a pager, triaged incidents, felt the 2AM stress
Someone with strong product instincts who turns fuzzy problems into concrete solutions
Technically capable across the stack - backend, integrations, frontend when needed
A driver, not a passenger. You fix problems when you see them, not when you're asked.
Nice to have
Developer tools, observability, or infrastructure background
Experience with AI/ML products, especially evaluation and improvement loops
Startup experience
You'll work directly with Cleric's founders on product and technical direction. We're small enough that you can directly influence what we ship from day one.
Small team, full ownership
Direct feedback, no politics
In-person in SF
AI-native: we build with AI constantly
Intro call – Background, technical screen, questions on the role
Build session (1 hr) - Pair programming with another Cleric engineer
System design (90 min) - Work through a real production problem we have
Product deep-dive (60 min) - Talk through a real scenario, real tradeoffs
Team lunch/coffee - Hard questions, both directions
Top Skills
What We Do
Cleric is an AI-powered agent designed to manage and resolve issues in production environments autonomously. It uses an LLM based reasoning engine to react to, interpret, and implement solutions to production issues.
