The Cortex Code team is building the future of coding agents for working with data. As a Staff MLE/AI Engineer on Cortex Code Quality, 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.
What you will do in this role:
Own major pillars of the quality stack: tuning agent behavior to engage on next generation agentic coding tasks.
Design and evolve pipelines and tooling that support large-scale experimentation, error mining, and iteration on prompts/tools/workflows with clear before/after signals.
Lead postmortems on quality regressions; cluster failure modes; translate findings into a prioritized roadmap for engineering and modeling partners.
Align product, infra, and applied AI on what "good" means for critical customer workflows; mentor engineers and uplevel eval craft across the team.
Ensure quality systems are dependable in practice—reproducible runs, stable datasets, versioning, and operational clarity when things drift.
Requirements:
Bachelor's degree in Computer Science, Engineering, Statistics, or a related field. Master's or higher preferred but not a requirement.
8+ years of experience shipping AI/ML-backed software in production, including Staff-level ownership of technical direction, cross-team delivery, and mentoring.
Strong track record building and operating eval harnesses, measurement, and/or experimentation loops for LLM/agent systems—not only one-off benchmarks.
Proficiency in programming languages such as Python, TypeScript, Go (strong in at least two).
Exceptional communication skills: crisp writeups, constructive debate, and ability to influence without authority across engineering and product.
(Optional) Experience with data engineering pipelines (dbt, Airflow), data modeling, data analysis, retrieval systems, and semantic layers is a plus.
Nice to have:
Deep experience with agentic coding tools (IDE agents, CLI agents) and intuition for model strengths, failure modes, and prompting limits.
Background in data engineering (dbt, Airflow), analytics, retrieval / RAG, or semantic layers—highly relevant for data-centric coding agents.
Prior work on LLM observability, safety/guardrails, or quality systems used as release gates in production.
You may be a particularly good fit if you:
Have built and owned complex quality + data pipelines—substantial state, branching logic, and operational requirements.
Thrive in high-intensity environments with short feedback loops and high standards for rigor.
Take ambiguous "quality is slipping" problems to completion: you care about clear metrics, reproducibility, and sustained improvement—not one-off score bumps.
Are a power user of modern coding agents and care about turning intuition into systematic measurement and team-wide practice.
About Snowflake
Snowflake is the AI Data Cloud trusted by the world's most innovative companies. We're shipping production-ready AI applications at scale and want you to join us in building the future of how businesses interact with their data through Cortex Code, Cortex agents, Cortex analyst, Cortex search.
Every Snowflake employee is expected to follow the company's confidentiality and security standards for handling sensitive data. Snowflake employees must abide by the company's data security plan as an essential part of their duties. It is every employee's duty to keep customer information secure and confidential.
Snowflake is growing fast, and we're scaling our team to help enable and accelerate our growth. We are looking for people who share our values, challenge ordinary thinking, and push the pace of innovation while building a future for themselves and Snowflake.