Staff, Software Engineer

Walmart · Retail · Sunnyvale, CA

Staff Software Engineer role focused on architecting and building scalable, enterprise-grade solutions using Java, Spring Boot, React, and agentic technologies leveraging LLMs and MCPs. The role involves building and optimizing intelligent agents, ensuring they are observable, cost-effective, and deliver consistent quality through evaluation pipelines, while integrating with Walmart’s core tech platforms.

What you'd actually do

  1. Design and own the technical architecture ensuring the system scales with business complexity and evolve the MCP server's technical foundation—connection management, async patterns, service boundaries—ensuring the system scales reliably under load.
  2. Build robust APIs and integrations that enable seamless data flow across systems.
  3. Build and optimize intelligent agents using DSPy/LLM frameworks, ensuring they are observable, cost-effective, and deliver consistent quality through evaluation pipelines.
  4. Ensure the system performs efficiently at scale through proactive optimization.
  5. Own the operational excellence of the system—deployment, configuration, monitoring, security—ensuring production reliability and performance.

Skills

Required

  • Python
  • Java
  • Spring Boot
  • React
  • PostgreSQL / Azure SQL
  • modern agentic technologies (LLMs, MCPs)
  • design and development of highly scalable distributed applications and platforms
  • design and deliver scalable, enterprise-grade solutions integrating with Walmart’s core tech platforms
  • problem-solving and automation mindset
  • collaboration and communication skills
  • leading technical initiatives that drive platform unification, data integration, operational excellence, engineering excellence, alerting and monitoring / tracing

Nice to have

  • DSPy

What the JD emphasized

  • agentic technologies
  • LLMs
  • MCPs
  • intelligent agents
  • evaluation pipelines
  • highly scalable distributed applications and platforms
  • modern agentic technologies (LLMs, MCPs)
  • intelligent workflow transformation
  • operational excellence
  • alerting and monitoring / tracing

Other signals

  • building intelligent agents
  • leveraging LLMs
  • agentic technologies