Staff Software Engineer, GitHub Intelligence (Copilot Agents)

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Staff Software Engineer, GitHub Intelligence (Copilot Agents) based in United States. This is a staff-level engineering role focused on advancing the infrastructure that enables AI agents to understand and use software-development context effectively. You will help build intelligent context capabilities spanning agent memory, search, knowledge graphs, retrieval, and connected developer tools. Your work will influence how AI agents reason across code, issues, pull requests, workflows, and other development signals. You will turn ambiguous product challenges into scalable architectures, technical strategies, experiments, and production systems. The role combines deep hands-on engineering with technical leadership and close collaboration across product, research, design, and data science. You will help establish evaluation and feedback systems that improve agent quality, reliability, efficiency, and customer outcomes. Your contributions will have the potential to shape AI-assisted software development for millions of developers and organizations worldwide. Provide technical leadership for systems that enable AI agents to acquire, interpret, retain, and apply relevant software-development context. Design, prototype, implement, test, deploy, and operate scalable production systems supporting agent experiences and developer workflows. Build platform capabilities and APIs covering context retrieval, sessions, memory, agent customization, evaluation, and feedback-driven improvement. Translate ambiguous customer and product opportunities into clear technical strategies, architecture proposals, experiments, and executable roadmaps. Develop approaches that improve how software is built with AI agents and help engineering teams work more effectively. Partner with product managers, designers, researchers, data scientists, and engineers to deliver cohesive end-to-end experiences. Establish evaluation methodologies, telemetry, and learning loops to measure agent quality, efficiency, reliability, and customer impact. Make informed trade-offs across performance, latency, cost, privacy, security, reliability, and developer experience. Use debugging tools, operational data, and structured experimentation to identify bottlenecks and continuously improve system performance and maintainability. Own the reliability and quality of systems, including participation in first-responder on-call rotations and incident management where applicable. Provide mentorship through design and code reviews, technical guidance, pairing, and knowledge sharing. Influence engineering practices and architectural decisions across organizational boundaries while promoting operational and executional excellence. Foster an inclusive, collaborative environment where engineers have clear ownership and are empowered to deliver high-quality work. Requirements: 9+ years of professional experience in software engineering, computer science, or a related technical discipline, with demonstrated experience building and maintaining production software. Equivalent experience may include an associate degree with 8+ years of relevant experience, a bachelor’s degree with 7+ years, a master’s degree with 5+ years, or a doctorate with 3+ years of relevant experience. Strong production programming experience in one or more languages such as C, C++, C#, Java, JavaScript, Go, Ruby, Rust, Python, or TypeScript. Experience with information retrieval, context retrieval, knowledge graphs, semantic systems, personalization, persistent knowledge, or memory systems is highly valuable. Experience designing or integrating production AI-agent or generative-AI capabilities, including model orchestration, retrieval-augmented generation, tool use, evaluation, or feedback loops. Strong ability to define technical direction and influence architecture across multiple teams or organi