Staff Software Engineer, AI Developer Tools

Gusto Gusto · Fintech · Denver, CO +3 · Remote · Engineering

Staff Software Engineer on the AI Developer Tools team at Gusto, responsible for architecting the AI platform to accelerate engineering across the organization. Focuses on multi-agent systems, RAG, and intelligent automation to eliminate developer friction and improve productivity.

What you'd actually do

  1. Architect AI Core Infrastructure: Design, scale, and maintain the internal platform and APIs that integrate LLMs into the developer workflow, with a heavy focus on autonomous agents, custom retrieval-augmented generation (RAG), and smart context-delivery systems.
  2. Drive Technical Leadership & Vision: Establish engineering best practices for building with AI at Gusto, including robust evaluation frameworks (evals), guardrails for code safety, and strategies for optimizing model latency and token spend.
  3. Collaborate & Evangelize: Partner closely with product engineering teams to uncover systemic friction points, and collaborate with core Infrastructure and Security teams to ensure all AI tooling is scalable, compliant, and secure.
  4. Optimize Feedback Loops: Identify and eliminate critical bottlenecks in the local-to-production lifecycle at scale across Gusto.
  5. Maintain Enterprise Reliability: Treat AI infrastructure with production-grade rigor. Monitor system health, diagnose complex integration or networking issues, and mitigate model drift or downtime.

Skills

Required

  • Systems Expertise (8+ years)
  • Production AI Experience
  • Prompt Engineering
  • Fine-tuning
  • RAG Architectures
  • Multi-agent Workflows
  • Developer Experience and Productivity
  • Data Privacy
  • Security
  • Cost Management
  • Systemic Reliability
  • Communication
  • Mentoring
  • Stakeholder Alignment

Nice to have

  • Architecting AI Core Infrastructure
  • LLM Integration
  • Autonomous Agents
  • Retrieval-Augmented Generation (RAG)
  • Context-Delivery Systems
  • Evaluation Frameworks (evals)
  • Guardrails for Code Safety
  • Model Latency Optimization
  • Token Spend Optimization
  • Scalable AI Tooling
  • Compliant AI Tooling
  • Secure AI Tooling
  • Feedback Loop Optimization
  • Production-Grade AI Infrastructure
  • System Health Monitoring
  • Complex Integration Diagnosis
  • Networking Issue Diagnosis
  • Model Drift Mitigation
  • Downtime Mitigation

What the JD emphasized

  • architectural anchor
  • AI-native development lifecycle
  • eliminate developer friction
  • multi-agent systems
  • intelligent automation
  • building bespoke internal coding assistants
  • automating sprawling codebase refactors
  • deploying AI to self-heal CI/CD pipelines
  • multiply the velocity of hundreds of builders
  • next generation of AI tools
  • AI Developer Tools team
  • provide every builder at Gusto with a suite of "superpowers" tools
  • deeply understand our codebase
  • absorb operational toil
  • focus on creative problem-solving
  • treat our fellow engineers as our primary customers
  • prioritizing developer experiences
  • absolutely delightful to use
  • Architect AI Core Infrastructure
  • integrate LLMs into the developer workflow
  • autonomous agents
  • custom retrieval-augmented generation (RAG)
  • smart context-delivery systems
  • Drive Technical Leadership & Vision
  • engineering best practices for building with AI
  • robust evaluation frameworks (evals)
  • guardrails for code safety
  • optimizing model latency and token spend
  • Collaborate & Evangelize
  • partner closely with product engineering teams
  • uncover systemic friction points
  • collaborate with core Infrastructure and Security teams
  • ensure all AI tooling is scalable, compliant, and secure
  • Optimize Feedback Loops
  • identify and eliminate critical bottlenecks
  • local-to-production lifecycle at scale
  • Maintain Enterprise Reliability
  • production-grade rigor
  • Monitor system health
  • diagnose complex integration or networking issues
  • mitigate model drift or downtime
  • 8+ Years of Systems Expertise
  • seasoned engineer
  • highly comfortable navigating massive, complex codebases
  • delivering production-grade, distributed software
  • Production AI Experience
  • proven track record of moving AI beyond prototypes
  • deep understanding of prompt engineering
  • fine-tuning
  • RAG architectures
  • orchestrating multi-agent workflows
  • Developer-First Mindset
  • passionate about Developer Experience and Productivity
  • intuitively understand what makes an internal tool frictionless, fast, and empowering for other engineers
  • Strategic Execution
  • think deeply about data privacy, security, cost management, and systemic reliability
  • deploying AI solutions
  • Exceptional Communication
  • seamlessly translate bleeding-edge AI capabilities into clear, actionable infrastructure strategies
  • mentoring junior engineers
  • aligning cross-functional stakeholders
  • Working as a Team
  • work across team boundaries
  • bring other teams and groups along with you towards our strategic vision

Other signals

  • architecting AI platform for engineering productivity
  • multi-agent systems
  • RAG
  • developer tools