Snowflake

Principal /Staff AI Engineer - Cortex Code Agentic System

Menlo Park, California, United StatesFull timeStaff$236,000 - $339,200 / yearPosted 12 days ago
Apply on Snowflake →

Sign into see who you know at Snowflake.

At Snowflake, we are powering the era of the agentic enterprise. To usher in this new era, we seek AI-native thinkers across every function who are energized by the opportunity to reinvent how they work. You don’t just use tools; you possess an innate curiosity, treating AI as a high-trust collaborator that is core to how you solve problems and accelerate your impact. We look for low-ego individuals who thrive in dynamic and fast-moving environments and move with an experimental mindset — who rapidly test emerging capabilities to discover simpler, more powerful ways to deliver results. At Snowflake, your role isn't just to execute a function, but to help redefine the future of how work gets done.

About the Role

The Cortex Code team is building the future of coding agents for working with data. See our flagship product in action: Cortex Code in Action: Live Demos + AMA https://www.youtube.com/watch?v=YLGL0MU5AXQ.

As a Staff/Principal AI Engineer on Cortex Code , you will help define architect agent behavior at enterprise scale by building the agentic systems and methodology that make our users build cutting edge agentic systems that are efficient, repeatable, auditable, and shippable. You’ll partner with modeling, platform, and product leadership to turn customer pain into golden scenarios, metrics, and experiment loops that the whole team can trust.

Responsibilities:

- Agent strategy & systems: Own major pillars of the quality stack: tuning agent behavior to engage on next generation agentic coding tasks.

- Hill-climb infrastructure: Design and evolve pipelines and tooling that support large-scale experimentation, error mining, and iteration on prompts/tools/workflows with clear before/after signals.

- Deep analysis & prioritization: Lead postmortems on quality regressions; cluster failure modes; translate findings into a prioritized roadmap for engineering and modeling partners.

- Cross-functional leadership: Align product, infra, and applied AI ...