Example scenarios:

• "Implementing a custom retry decorator with exponential backoff and jitter for an unreliable downstream service."
• "Writing a thread-safe in-memory message queue that supports priority-based message processing."

3. System Design

The system design session at Cleric focuses on distributed systems, scalability, and the unique challenges of building agentic workflows. You will need to design systems that are both highly scalable and highly secure.

Be ready to go over:

• Agent execution environments – Designing secure, isolated runtimes (like sandboxed containers) where an LLM can safely run code.
• API & Integration architectures – How to build a system that can dynamically connect to and query arbitrary third-party monitoring systems (like Datadog, Prometheus, or Splunk).
• Observability and evaluation loops – How to store, replay, and evaluate long-running agent trajectories to measure performance improvements.
• Advanced concepts – State distribution in agentic networks, real-time streaming of agent thoughts/logs, and rate-limit mitigation strategies across multiple LLM providers.

Example scenarios:

• "Designing the backend architecture for an agent that needs to query Kubernetes logs, analyze them, and execute a rollback command safely."
• "Architecting a high-throughput logging system that captures and indexes every tool call and LLM prompt/response for auditing."

As a Software Engineer at Cleric, your day-to-day work will span across core backend engineering, systems programming, and AI integration. You will have a high degree of ownership over major product areas.

• Develop Agent Capabilities – Design and implement the reasoning loops and tool execution workflows that allow the agent to autonomously navigate systems, execute terminal commands, run database queries, and read logs.
• Build Production Integrations – Write robust, secure integrations with cloud infrastructure (AWS, GCP, Kubernetes) and observability tools (Datadog, New Relic, Prometheus) so the agent can interact with customer environments.
• Create Observability & Evaluation Tooling – Build internal systems to monitor, evaluate, and benchmark the performance of the AI agent, ensuring that updates to the underlying LLMs improve reliability without introducing regressions.
• Collaborate on System Architecture – Work alongside senior engineers to scale the backend runtime systems, ensuring high availability, low latency, and strict security boundaries for agent actions.
• Maintain High Engineering Standards – Champion clean code, thorough testing, and robust documentation. Participate in radical candor code reviews to maintain a high bar for system reliability.

Cleric is looking for exceptional engineers who are highly motivated, fast learners, and comfortable with ambiguity. The team is small, meaning every engineer must be capable of operating independently and driving projects to completion.

Must-Have Qualifications

• Professional Experience – 1–2 years of professional software engineering experience, ideally working on backend systems.
• Language Proficiency – Strong, production-grade programming experience in Python. You should be deeply familiar with its asynchronous ecosystem, testing frameworks, and performance characteristics.
• CS Fundamentals – A rock-solid understanding of software engineering fundamentals, data structures, algorithms, and system design patterns.
• Drive & Adaptability – A strong interest in AI, ML, and agentic systems, combined with a desire to learn rapidly and ship code directly to production.

Nice-to-Have Qualifications

• AI/ML Exposure – Prior experience working with LLM APIs, prompt engineering, vector databases, or building LLM-based products.
• Infrastructure Experience – Familiarity with distributed systems, cloud infrastructure (AWS/GCP), containerization (Docker, Kubernetes), or modern DevOps/SRE tooling.
• Startup Background – Experience working in a fast-paced, high-growth startup where priorities can shift quickly and ownership is highly distributed.

Q: Do I need a background in Machine Learning or AI to apply? A: No. While an interest in AI and agentic systems is required, this is primarily a backend and systems engineering role. The core challenges at Cleric involve building the robust infrastructure, integrations, and runtime environments that allow AI models to interact with the physical world safely and reliably.

Q: What is the working style at Cleric? A: Cleric operates with an in-person collaboration model in their San Francisco office. They believe that high-bandwidth, face-to-face communication is critical for moving fast and solving complex, open-ended problems. The team embraces a culture of radical candor, where feedback is direct, constructive, and aimed at building the best possible product.

Q: How should I prepare for the 30-second tool demo in the Loom video? A: Choose a tool you actually use daily and know intimately. It does not need to be highly obscure; it just needs to show that you care about developer productivity and command-line efficiency. Examples include a custom git alias, a jq command for parsing JSON, or an fzf configuration for fast terminal navigation. Explain what it does, show it in action, and explain why it saves you time.

Q: What is the "Bar Raiser" round? A: The Bar Raiser round focuses on your engineering practices, product mindset, and cultural alignment. Interviewers will explore how you handle feedback, your experience working in collaborative teams, and how you think about product quality. They want to ensure you align with Cleric’s values of high impact, rapid iteration, and radical candor.

To truly stand out during the Cleric interview process, keep these practical, insider tips in mind:

• Showcase SRE Empathy: Because Cleric's core product is an autonomous incident responder, always look at engineering problems through the lens of an SRE. Ask yourself: How would I monitor this? How would I debug this if it failed silently? How do we prevent this from waking up an engineer at 3 AM?
• Embrace Radical Candor: During technical discussions and behavioral rounds, be direct, honest, and open about what you don't know. If your design has a weakness, point it out before the interviewer does. The team values self-awareness and direct communication far more than defensive positioning.

• Focus on Safety in System Design: When designing systems that allow AI agents to execute code or run commands, safety is paramount. Always build in guardrails, sandboxing, and human-in-the-loop validation mechanisms. Proactively discussing how to prevent an agent from accidentally running rm -rf or dropping a production database will show you understand the gravity of Cleric's domain.
• Be Ready to Iterate: If an interviewer challenges your code or your system design, do not get defensive. Treat it as a collaborative debugging session. Cleric values engineers who can take feedback in real-time, pivot their approach, and iterate toward a better solution quickly.

The Software Engineer role at Cleric offers an extraordinary opportunity to shape the future of software reliability and autonomous AI. By building the infrastructure that allows AI agents to safely investigate and resolve production outages, you will help solve one of the most painful and costly challenges in modern technology.

To maximize your chances of success, focus your preparation on core backend engineering, robust system integration, and production debugging patterns. Make sure your Loom video submission is polished, concise, and demonstrates a genuine passion for high-quality engineering tools and systems.

The compensation details above represent the competitive salary ranges offered for engineering positions at Cleric in San Francisco. When evaluating your offer, remember that Cleric also offers meaningful equity packages, allowing you to share directly in the long-term success of the company as it scales.

Approach your interviews with confidence, clarity, and a collaborative mindset. The team at Cleric is looking for peers who want to push the boundaries of what AI can do in production environments. Prepare thoroughly, show your passion for building resilient systems, and demonstrate your readiness to make a massive impact from day one. Good luck!