Staff Software Engineer (AI)

Location: Menlo Park, California, United States

Salary: $236,000–$295,000 per year

Company

Snowflake develops enterprise data and AI products, including production-grade LLM applications, intelligent agents, AI infrastructure, and evaluation systems for sensitive data at scale.

What you will do

• Architect and build an Agentic Harness for complex, multi-step AI workflows across models, tools, data, and services.
• Design interfaces for tool execution, context construction, state and memory management, permissions, retries, fallbacks, and human review.
• Build evaluation harnesses, representative datasets, automated graders, experiment pipelines, release gates, and replay infrastructure.
• Analyze production agent trajectories and incidents to identify failures in reasoning, retrieval, tool use, context, orchestration, and application code.
• Develop measurements for task completion, correctness, groundedness, safety, latency, reliability, and cost while improving agent efficiency.
• Set technical direction across teams, productionize secure and observable multi-tenant services, mentor engineers, and remain involved in implementation and debugging.

Requirements

• 9+ years of software engineering experience, including technical leadership of complex production systems.
• Direct experience shipping and operating LLM applications, AI agents, or model-backed workflows in production.
• Strong background in distributed systems, service architecture, high-throughput APIs, concurrency, and failure handling.
• Fluency in Python and strong proficiency in at least one of Java, Go, Rust, or TypeScript.
• Hands-on knowledge of tool calling, structured generation, retrieval, context engineering, prompt management, model APIs, and production observability.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

Nice to have

• Experience building evaluation or observability infrastructure for agentic coding, data engineering, or analytics systems.
• Experience with human-evaluation programs, grader calibration, multi-agent orchestration, asynchronous workflows, simulations, adversarial testing, or safety guardrails.
• Experience with vector or hybrid search, semantic indexing, ranking, caching, and retrieval systems.
• Experience operating multi-tenant systems handling sensitive enterprise data and working with databases, SQL engines, Kubernetes, or cloud-native infrastructure.

Culture & Benefits

• Work in a fast-moving environment centered on experimentation and measurable customer outcomes.
• Collaborate across product, infrastructure, applied AI, security, and modeling teams.
• Use production behavior and representative tasks to guide evaluation and engineering decisions.
• Help establish standards for evaluation design, sampling, ground-truth quality, grader calibration, leakage prevention, and statistical significance.