Senior Software Engineer, Agentic AI Systems

Overview

• At NVIDIA, we are building the next generation of AI-native software systems.
• As AI evolves from assistant-based workflows to autonomous systems capable of reasoning, planning, and acting, we are looking for exceptional engineers to help define and build the underlying platforms that power this transformation.
• As a Senior Software Engineer, Agentic AI Systems, you will design and develop production-scale AI systems that combine large language models, retrieval, memory, orchestration, evaluation, and tools into intelligent software capable of solving complex real-world problems.
• This role sits at the intersection of AI, distributed systems, software engineering, and developer productivity.
• What You'll Be Doing: Design and implement intelligent systems that can reason, plan, and execute complex multi-step workflows.
• Develop architectures that combine LLMs, retrieval systems, memory, tools, and feedback loops.
• Build autonomous and semi-autonomous workflows that improve engineering productivity and operational efficiency.
• Design scalable backend services, APIs, and distributed systems supporting AI-native applications.
• Build orchestration frameworks for multi-agent and tool-based systems.
• Develop evaluation frameworks that measure accuracy, reliability, latency, and task completion.
• Partner with AI researchers, infrastructure teams, product teams, and software engineering organizations.
• What We Need To See: BS, MS, or PhD in Computer Science, Computer Engineering, or a related field.
• 5+ years of software engineering experience.
• Strong proficiency in Python and modern software development practices.
• Experience building scalable distributed systems and cloud-native services.
• Experience developing AI-enabled applications using LLMs, RAG, agent frameworks, or workflow orchestration systems.
• Proven experience designing, building, and operating large-scale production software systems.
• Strong understanding of distributed systems, scalability, reliability, observability, and performance engineering.
• Demonstrated ability to own services from architecture and implementation through production operations and long-term maintenance.
• Ability to balance rapid innovation with engineering rigor, maintainability, and operational excellence.
• Ways To Stand Out From The Crowd: Experience building production AI agents or autonomous systems.
• Experience with reasoning frameworks, planning systems, memory architectures, and tool-use ecosystems.
• Experience with vector databases, retrieval systems, knowledge graphs, or semantic search.
• Experience with AI evaluation, benchmarking, and observability platforms.
• Built and operated business-critical platforms serving large user bases or high-volume workloads.
• Experience modernizing early-stage prototypes into robust production systems.
• Deep expertise in system architecture, reliability engineering, and technical leadership.Track record of reducing operational complexity while increasing scalability and maintainability.
• We are looking for engineers who can build systems, not just features.
• The ideal candidate has experience architecting and operating large-scale, production-grade software that remains reliable, maintainable, and extensible as it grows.
• While AI expertise is valuable, we place equal importance on strong software engineering fundamentals, system design, operational excellence, and long-term ownership.
• We are looking for engineers who see AI agents not as prompts, but as software systems.