About the role
Join Our Innovative Team at Cleric
At Cleric, we are revolutionizing the way engineering teams operate by developing an autonomous, self-learning AI Site Reliability Engineer (SRE). Our cutting-edge agent empowers teams to investigate production incidents up to 10 times faster than traditional methods. With capabilities to analyze logs, correlate metrics, and reason through hypotheses, our AI SRE identifies real issues with an impressive accuracy rate of over 78% in high-scale environments.
Our users have embraced this technology, and we aim to establish Cleric as the go-to solution for engineers when critical situations arise.
About the Role
Pioneering the Future of AI SRE
As a Staff Software Engineer, you will define the future of AI SRE, tackling complex challenges without a predefined roadmap. You will be responsible for addressing pivotal questions such as:
How can engineers maintain their skills for scenarios the AI cannot handle?
What strategies are effective in building trust when agent conclusions need verification at 2 AM?
Your insights will be shaped through direct interactions with engineers, product experiments, and strategic planning to guide Cleric's approach to problem-solving.
In this role, you will collaborate closely with the founders to establish the product's trajectory. You will enjoy significant technical autonomy, making decisions on architecture, system design, and addressing areas that require improvement.
Your Responsibilities
Develop systems that facilitate investigations: data flows, integration points, and how agent insights are presented to engineers.
Engage directly with engineers during calls, in war rooms, and while observing live debugging to inform product direction.
Establish criteria for successful investigations, identify gaps, and collaborate with AI engineers to address them.
Conduct experiments to explore innovative ways to present findings, gauge engineer trust, and adapt strategies based on feedback.
Make informed technical decisions across the stack, including Python, integrations, and frontend components, taking full ownership of outcomes.
Set engineering standards that enable rapid deployment while ensuring high quality.
About You
You are an engineer with experience owning products from conception to implementation, capable of articulating the reasoning behind successful features.
You have firsthand experience with production challenges, having carried a pager, triaged incidents, and felt the pressure of critical situations.
You possess strong product instincts, adept at transforming ambiguous challenges into clear, actionable solutions.

