Software Engineer - Agents for Code

Snowflake•Menlo Park, CA

About The Position

Snowflake is about empowering enterprises to achieve their full potential — and people too. With a culture that’s all in on impact, innovation, and collaboration, Snowflake is the sweet spot for building big, moving fast, and taking technology — and careers — to the next level. The Cortex team is leveraging coding agents to accelerate user workflows. Our mission is to build autonomous, agentic systems that augment and automate complex coding, migration, and testing workflows. Your work will directly impact the speed at which the world’s largest companies modernize their data stacks. You will work within a high-powered team of engineers and scientists. You'll own the full AI engineering lifecycle: design, prompt/tool engineering, evals, deployment, measurement, and optimization.

Requirements

Education: Bachelor’s degree in Computer Science, Engineering, or a related field.
Experience: 1-3 years of software engineering experience, with a strong interest or project experience in shipping AI/ML features or LLM-based applications.
Technical Proficiency: Strong programming skills in Python and experience with SQL (Snowflake, SQL Server, Oracle, or Teradata experience is a plus).
AI Fundamentals: Familiarity with AI engineering and agentic workflows.
Communication: Strong communication skills and ability to collaborate effectively in a team environment.

Responsibilities

Build Agentic Systems: Build sophisticated agents and tools for migrating SQL and ETL pipelines from legacy systems for customers adopting snowflake.
Quality Improvements: Create "golden sets" and rubrics to measure the accuracy of AI-driven processes across various workflows. "Hillclimb" on metrics to optimize agentic systems.
Scale Automated Coding: Scale automated coding agents to reduce human effort by 90%.
Design & Execute Evals: Collaborate with FDE and Product: Partner with Forward Deployed Engineers (FDEs) and other product teams to translate real-world challenges into automated product features, ensuring a rapid feedback loop for tooling improvements.