Senior Software Engineer, Cortex Quality

Snowflake
Menlo Park
Workplace: OnsiteFull timeUSD 200,000 - 270,000 annuallyFunction: Software EngineeringExperience: 6+ yearsEducation: bachelorsSkills: ["Measurement-first thinking","Systems thinking","Debugging","Communication","Collaboration"]

Own end-to-end quality for Cortex Code, Snowflake’s coding agent for data-driven workflows. You’ll measure agent performance and reliability in production, build eval harnesses, diagnose failure modes from real trajectories, and run experiments to improve quality, cost, and latency. Collaborate with product and infrastructure to debug production issues, create robustness through regression tests, and feed real task insights back into modeling and evals.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Snowflake
Snowflake
7 hours ago

Senior Software Engineer, Cortex Quality

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 6 hours agoStatus: Live

Job Summary

Own end-to-end quality for Cortex Code, Snowflake’s coding agent for data-driven workflows. You’ll measure agent performance and reliability in production, build eval harnesses, diagnose failure modes from real trajectories, and run experiments to improve quality, cost, and latency. Collaborate with product and infrastructure to debug production issues, create robustness through regression tests, and feed real task insights back into modeling and evals.
Location: Menlo Park
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Mid level

Key Responsibilities

  • •Take Cortex Code agents from prototype to production by designing and refining reliable behaviors for real coding and data-engineering workflows.
  • •Own agent quality end to end: build eval harnesses, diagnose failure modes from real agent trajectories, and run experiments to improve key metrics.
  • •Drive down cost and latency without regressing quality using prompt caching, context compaction, tool-result offloading, and cheaper model routing.
  • •Debug production failures and improve robustness by closing the loop from broken runs to fixes and regression tests.
  • •Build data pipelines feeding real-world task insights back into evals and modeling.

Pay and Benefits

Salary: USD 200,000 - 270,000 annually

Key Requirements

  • •Bachelor’s degree in Computer Science, Engineering, Statistics, or a related field (Master’s preferred).
  • •6+ years shipping software in production, including AI/LLM features.
  • •Fluency in at least one of Python, TypeScript, or Go, with willingness to work across all three.
  • •Measurement-first, systems-thinking approach to designing reliable evals (sampling, ground-truth quality, leakage, noise).
  • •Comfort debugging complex, unpredictable, real-world production failures.
Experience:6+ yearsAI/LLM
Education:Bachelor's in Computer Science, Engineering, Statistics
Skills:Measurement-first thinkingSystems thinkingDebuggingCommunicationCollaboration
Tech Stack:PythonTypeScriptGoAI/LLMEval harnessesPrompt cachingContext compactionTool-result offloadingModel routingLLM observabilitySafety/guardrailsData engineeringData modelingAnalyticsRetrieval/RAGSemantic layersPipelinesOrchestration

Company Brief

Snowflake
Provides a cloud-native data platform for data warehousing, data engineering, data science, and analytics, enabling organizations to store, process, and share large-scale data across multiple cloud providers with elastic scalability and performance.
Industry: Data Infrastructure
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Bozeman, United States
Founded: 2012
WebsiteLinkedIn