Staff Software Engineer, Agentic

About the Role

Agentic Pods is pioneering a new way for Engineering to partner with teams across Uber and transform how work gets done through AI. Our engineers embed directly with operational teams to understand complex workflows, reimagine what's possible with agentic AI, and build production-grade systems that turn those opportunities into reality.

We are looking for an Agentic Software Engineer to design, build, and operate intelligent, reliable agentic systems that transform complex operational workflows at scale.

This role sits at the intersection of backend engineering, production reliability, and applied AI, combining deep technical ownership with a forward-deployed engineering approach. You'll work closely with operators and domain experts to identify high-impact opportunities, determine where AI agents can safely and effectively improve workflows, and translate ambiguous business challenges into scalable, production-ready solutions.

You'll own the full engineering lifecycle, from problem discovery and system architecture to implementation, deployment, and continuous improvement. This is an opportunity to shape how Uber applies agentic AI to real-world operations while helping establish the technical foundations for broader adoption across the company.

What You'll Do

Design and Build Agentic Systems

• Partner directly with operational teams to understand complex workflows, identify inefficiencies, and determine where AI agents, traditional automation, or human decision-making can deliver meaningful improvements.
• Design, develop, and deploy production-grade agentic systems, including AI agents, reusable skills, backend services, APIs, system integrations, data pipelines, and human-in-the-loop workflows.
• Rapidly prototype, validate, and iterate on solutions with real users, translating ambiguous requirements into reliable, scalable software.

Own Production Reliability and Performance

• Design systems with reliability, scalability, and operational resilience in mind, establishing clear performance and quality standards.
• Build comprehensive observability across agent behavior, model outputs, system dependencies, and workflow outcomes using tracing, logging, metrics, monitoring, and alerting.
• Own systems throughout their production lifecycle, troubleshooting failures, implementing recovery mechanisms, and continuously improving performance based on operational insights and user feedback.

Build Safe, Measurable, and Trustworthy AI Systems

• Develop evaluation frameworks to measure agent effectiveness, including task completion, output quality, tool selection, policy compliance, and failure handling.
• Implement testing and validation strategies across development, controlled rollouts, and production environments to ensure consistent and predictable system behavior.
• Design appropriate safeguards, including access controls, human approvals, auditability, data protection, reversible actions, and escalation mechanisms.
• Collaborate with Security, Privacy, Legal, and Data teams to ensure AI-powered workflows meet Uber's standards for safety, compliance, and operational integrity.

Drive Reusability and Engineering Excellence

• Identify opportunities to transform individual solutions into reusable agent capabilities, shared services, platform components, and standardized integration patterns.
• Design flexible architectures that support different business needs and regional requirements without unnecessary duplication.
• Contribute to engineering standards, architecture decisions, development tooling, deployment practices, and reliability frameworks that enable Agentic Pods to scale effectively across Uber.

Who Thrives on This Team

We're looking for engineers who combine strong software engineering fundamentals with curiosity, ownership, and a passion for applying emerging technologies to real-world challenges.

• Agentic-first thinker: You see beyond existing workflows and recognize opportunities to fundamentally improve how work gets done using AI and automation.
• 0→1 builder: You thrive in ambiguous environments and can turn loosely defined problems into working, production-ready solutions.
• Product-minded engineer: You focus on solving meaningful user problems and understand that the best solution isn't always the most technically complex.
• Systems thinker: You balance immediate business needs with long-term scalability, reliability, and opportunities for reuse.
• Collaborative problem solver: You learn unfamiliar domains quickly, build strong relationships with stakeholders, and communicate effectively across technical and non-technical teams.

Minimum Qualifications

• PhD or equivalent in Computer Science, Engineering, Mathematics, or a related field and 2 years of full-time software engineering experience; or 5 years of full-time software engineering experience, including 3 years of specialized technical software engineering experience in one or more programming languages, such as C, C++, Java, Python, or Go.

  Note: The 3 years of specialized software engineering experience may be gained through education, full-time employment, additional training, coursework, research, or a combination of these. This experience is not necessarily in addition to the education and full-time work experience requirements listed above.

• Strong experience designing, developing, and deploying production backend or distributed systems, such as AI-enabled applications, orchestration platforms, APIs, asynchronous workflows, developer platforms, or enterprise integrations.
• Hands-on experience owning production systems, including monitoring, alerting, incident response, troubleshooting, failure recovery, and debugging across application, infrastructure, and data dependencies.
• Proficiency in at least one general-purpose programming language, such as Python, Go, Java, or C++.

Preferred Qualifications

• Hands-on experience building agentic AI applications or integrating large language models (LLMs) with tools, APIs, enterprise data sources, and permissioned systems.
• Familiarity with agent orchestration, evaluation frameworks, retrieval-augmented generation (RAG), context management, model routing, and AI safety controls.
• Experience in site reliability engineering (SRE), infrastructure, platform engineering, production engineering, or forward-deployed engineering environments.
• Experience designing and operating systems that support sensitive, business-critical, or operationally consequential workflows.
• Demonstrated ability to lead technical design, make architectural decisions, and influence engineering direction across teams.
• Strong problem-solving skills and the ability to collaborate directly with business stakeholders to translate complex operational challenges into technical solutions.

For San Francisco, CA-based roles: The base salary range for this role is USD $232,000 per year - USD $258,000 per year.

For Seattle, WA-based roles: The base salary range for this role is USD $232,000 per year - USD $258,000 per year.

For Sunnyvale, CA-based roles: The base salary range for this role is USD $232,000 per year - USD $258,000 per year.

For all US locations, you will be eligible to participate in Uber's bonus program, and may be offered an equity award & other types of comp. All full-time employees are eligible to participate in a 401(k) plan. You will also be eligible for various benefits.