[Remote] Senior Software Engineer - Agentic Memory

Note: The job is a remote job and is open to candidates in USA. NVIDIA’s Agentic Memory team is seeking a Senior Software Engineer with experience using, developing and researching agents in a variety of applications. The role involves designing evaluation methodologies, building data pipelines, and conducting experiments to enhance agentic memory systems.ResponsibilitiesDesigning novel benchmark tasks and evaluation methodologies that measure the effectiveness of agentic memory systems including semantic, episodic, and procedural memory across multi-session and multi-turn agent trajectoriesBuilding and maintaining synthetic dataset generation pipelines that produce realistic, enterprise-relevant evaluation data at scaleDesigning and running experiments to understand where agent memory falls short, diagnose root causes, and inform improvementsDeveloping and contributing to open-source evaluation harnesses that enable rigorous, reproducible comparison of memory system architecturesPartnering with teams across NVIDIA who are deploying agents to understand the role of memory in a variety of applications and help integrate improvementsContributing to public-facing benchmarks and leaderboards that advance the state of the art in agentic memory evaluationIntegrating our work to leverage and improve the full NVIDIA software ecosystem, working across team boundaries in the spirit of extreme codesignKeeping up to date with the latest developments in agentic memory across academia and industrySkillsMaster's degree (or equivalent experience) or PhD in Computer Science, Electrical Engineering, Artificial Intelligence, or Applied Math with 12+ years of experienceHands-on experience developing agentic systems and pipelines, with a preference for those that integrate and involve memoryAn understanding of the state of the art in retrieval research, with a focus on agentic retrievalKnowledge of best practices in batching, streaming, and scaling of large-scale data pipelines to support real-world applicationsExcellent Python programming skills and a strong understanding of the Python deep learning ecosystemAn ability to share and communicate your ideas clearly through blog posts, papers, GitHub, etcExcellent communication and interpersonal skills are required, along with the ability to work in a dynamic, product-oriented, distributed teamCandidates with a Master's, Ph.D. or equivalent experience in retrieval or multimodal research are preferredA history of mentoring junior engineers and interns is a plusA track record of publication in leading conferences like CVPR, ICLR, ICCV, ECCV, KDD, etcBenefitsEquityBenefitsCompany OverviewNVIDIA is a computing platform company operating at the intersection of graphics, HPC, and AI. It was founded in 1993, and is headquartered in Santa Clara, California, USA, with a workforce of 10001+ employees. Its website is https://www.nvidia.com.Company H1B SponsorshipNVIDIA has a track record of offering H1B sponsorships, with 448 in 2026, 1872 in 2025, 1354 in 2024, 976 in 2023, 835 in 2022, 601 in 2021, 529 in 2020. Please note that this does not guarantee sponsorship for this specific role.