Job Details

Mission

We are seeking an engineer to work at the intersection of Core Engineering and QA.

This role involves finding the patterns behind agentic AI software bugs, using the output of agentic V&V (verification and validation) systems to cluster faults, identify common root causes, and suggest remediations.

Role

Overview: This is a diverse role, starting from understanding the telemetry of failing agents, and moving into developing automated tools and methodologies for identifying and isolating faults, enabling our users (or their AI coding tools) to remediate faults so they can't happen again.

Fault Clustering: Analyze failed agent trajectories and group them into distinct root causes.

Fault Remediation: Harness software development best practices and coding agents to devise and prescribe long-term solutions for identified fault clusters in service of our users.

Qualities

• Code Detective: You get a rush out of condensing piles of fault data into a few simple, elegant fixes.
• AI & LLM Connoisseur: You are comfortable testing and bounding non-determinism and navigating the latest Python AI underpinnings.
• Statistics Sorcerer: You like to use data analysis tools and statistics to transform complex telemetry data into actionable root cause insights.
• Quality Quarterback: Robust, high-quality products and features are more important to you than trendy, hyped ones.

Bonus Points

• Experience with coverage-guided fuzz testing.
• A background in SRE or SDET, but you also like to code.

Experience

Experience with existing telemetry, logging, tracing, debugging, static / dynamic analysis (SAST), quality, testing, failure injection, performance monitoring, etc. tools.

Experience with developing AI or agentic systems or tools in Python.

About Us

We are an early-stage, stealth-mode agentic AI QA startup, backed by Breyer Zou Ventures and successful entrepreneurs, investors, and operators such as Scott Sandell, Sheryl Sandberg, Jerry Yang, and KR Sridhar.