Senior Software Engineer - Agentic Memory

Details

NVIDIA’s Agentic Memory team is seeking a Senior Software Engineer with experience using, developing, and researching agents in a variety of applications. You will join a team of researchers with deep experience in building information retrieval systems, working to advance the state of the art of agentic memory and improve agent performance across applications.

The role focuses on measuring and improving agentic memory (semantic, episodic, procedural) across multi-session and multi-turn agent trajectories, integrating work across the NVIDIA software ecosystem.

Responsibilities

• Design novel benchmark tasks and evaluation methodologies to measure the effectiveness of agentic memory systems (semantic, episodic, procedural) across multi-session and multi-turn agent trajectories.
• Build and maintain synthetic dataset generation pipelines that produce realistic, enterprise-relevant evaluation data at scale.
• Design and run experiments to understand where agent memory falls short, diagnose root causes, and inform improvements.
• Develop and contribute to open-source evaluation harnesses enabling rigorous, reproducible comparison of memory system architectures.
• Partner with teams across NVIDIA who are deploying agents to understand the role of memory in various applications and help integrate improvements.
• Contribute to public-facing benchmarks and leaderboards that advance the state of the art in agentic memory evaluation.
• Integrate work to leverage and improve the NVIDIA software ecosystem, working across team boundaries in the spirit of extreme codesign.
• Keep up to date with the latest developments in agentic memory across academia and industry.

Requirements

• Master’s degree (or equivalent experience) or PhD in Computer Science, Electrical Engineering, Artificial Intelligence, or Applied Math with 12+ years of experience.
• Hands-on experience developing agentic systems and pipelines, preferably those that integrate and involve memory.
• Understanding of the state of the art in retrieval research, with a focus on agentic retrieval.
• Knowledge of best practices in batching, streaming, and scaling large-scale data pipelines for real-world applications.
• Excellent Python programming skills and a strong understanding of the Python deep learning ecosystem.
• Ability to share and communicate ideas clearly (blog posts, papers, GitHub, etc.).
• Excellent communication and interpersonal skills; ability to work in a dynamic, product-oriented, distributed team. Mentoring junior engineers and interns is a plus.
• Candidates with a Master’s, PhD, or equivalent experience in retrieval or multimodal research and a track record of publications (CVPR, ICLR, ICCV, ECCV, KDD, etc.) are preferred.

Location and Working Model

Location is flexible; the team is remotely situated and focuses on North America / Europe time zones. Candidates are being considered in any country where NVIDIA has an office, and remote work is accepted.

Benefits

• Base salary range: 224,000 USD - 356,500 USD (determined based on location, experience, and pay of employees in similar positions).
• Eligibility for equity and NVIDIA benefits.

Other details

• Applications for this job will be accepted at least until April 12, 2026.
• NVIDIA uses AI tools in its recruiting processes and is an equal opportunity employer committed to diversity and non-discrimination.