Senior Software Engineer - Agentic Memory
NVIDIA · Texas, United States
- Hybrid
- Full-time
- $290,250 / year
- Texas, United States
Job highlights
- Develop advanced agentic memory systems.
- Design evaluation benchmarks and datasets.
- Improve AI agent performance and capabilities.
- Collaborate with NVIDIA's global teams.
- Advance state-of-the-art agent research.
About the role
Senior Software Engineer - Agentic Memory
NVIDIA's Agentic Memory team is seeking a Senior Software Engineer with experience using, developing, and researching agents in a variety of applications. You’ll join a team of researchers with deep experience in building information retrieval systems, who are now working on advancing the state of the art of agentic memory. At NVIDIA, we’re exploring the frontier of what agents are capable of and constantly pushing to improve them. Our work builds upon the efforts of dozens of teams in the NVIDIA ecosystem and focuses on measuring and improving the performance of agentic memory. Come be a part of our world-class team building the future of agents.
What You’ll Be Doing
- Designing 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 trajectories.
- Building and maintaining synthetic dataset generation pipelines that produce realistic, enterprise-relevant evaluation data at scale.
- Designing and running experiments to understand where agent memory falls short, diagnose root causes, and inform improvements.
- Developing and contributing to open-source evaluation harnesses that enable rigorous, reproducible comparison of memory system architectures.
- Partnering with teams across NVIDIA who are deploying agents to understand the role of memory in a variety of applications and help integrate improvements.
- Contributing to public-facing benchmarks and leaderboards that advance the state of the art in agentic memory evaluation.
- Integrating our work to leverage and improve the full NVIDIA software ecosystem, working across team boundaries in the spirit of extreme codesign.
- Keeping up to date with the latest developments in agentic memory across academia and industry.
What We Need To See
- 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, with a preference for those that integrate and involve memory.
- An 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 of large-scale data pipelines to support real-world applications.
- Excellent Python programming skills and a strong understanding of the Python deep learning ecosystem.
- An ability to share and communicate your ideas clearly through blog posts, papers, GitHub, etc.
- Excellent communication and interpersonal skills are required, along with the ability to work in a dynamic, product-oriented, distributed team.
- A history of mentoring junior engineers and interns is a plus.
- Candidates with a Master's, Ph.D. or equivalent experience in retrieval or multimodal research are preferred, along with a track record of publication in leading conferences like CVPR, ICLR, ICCV, ECCV, KDD, etc.
About NVIDIA and the Role
Location is flexible, and the team is remotely situated, focusing on NA/EU time zones. We are looking for candidates in any country where NVIDIA has an office, and remote work is accepted. GPU computing is the most productive and pervasive platform for deep learning and AI. It begins with the most advanced GPUs and the systems and software we build on top of them. We integrate and optimize every deep learning framework. We work with most major technology providers and support a broad range of Fortune 500 companies in their machine and deep learning needs. With deep learning, we can teach AI to do almost anything. New internet services, like Google Assistant, have learned speech from sound and provide a more natural way to access information. Self-driving cars use deep learning to recognize the space they inhabit, the lanes they drive in, and the objects to avoid. In healthcare, neural networks trained with millions of medical images can find clues in MRIs that until now could only be found through invasive biopsies. With competitive salaries and a generous benefits package, NVIDIA is widely considered to be one of the technology industry's most desirable employers. We work with some of the most forward-thinking, versatile people in the world, and our engineering teams are growing fast in some of the most impactful fields of our generation: Artificial Intelligence, Data Science, Deep Learning. If you're a creative engineer who enjoys autonomy and shares our passion for technology, we want to hear from you.
Compensation and Benefits
Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 224,000 USD - 356,500 USD. You will also be eligible for equity and benefits.
Key skills/competency
- Senior Software Engineer
- Agentic Memory
- Information Retrieval
- Machine Learning
- Python
- Deep Learning
- Data Pipelines
- Evaluation Methodologies
- Agentic Systems
- Large-scale Data
Skills & topics
- Senior Software Engineer
- Agentic Memory
- AI
- Machine Learning
- Deep Learning
- Information Retrieval
- Python
- Data Pipelines
- Evaluation
- Research Engineer
- Software Development
- NVIDIA
How to get hired
- Tailor your resume: Highlight your experience with agentic systems, memory integration, and large-scale data pipelines. Emphasize Python and deep learning expertise.
- Showcase your research: Include publications, GitHub contributions, and any open-source projects related to AI, agents, or retrieval.
- Demonstrate impact: Quantify your achievements in previous roles, especially in developing and evaluating complex systems.
- Prepare for technical interviews: Be ready to discuss your experience with agentic retrieval, data pipeline scaling, and Python deep learning frameworks.
- Understand NVIDIA's culture: Research their focus on AI, GPU computing, and collaborative, product-oriented environments.
Technical preparation
Behavioral questions
Frequently asked questions
- What specific experience is most valuable for the Senior Software Engineer - Agentic Memory role at NVIDIA?
- NVIDIA highly values hands-on experience in developing agentic systems and pipelines, particularly those involving memory integration. A strong understanding of state-of-the-art retrieval research, with a focus on agentic retrieval, is crucial. Experience with large-scale data pipeline best practices (batching, streaming, scaling) and excellent Python programming skills within the deep learning ecosystem are also key requirements.
- What academic background is preferred for this NVIDIA position?
- While a Master's degree or PhD in Computer Science, Electrical Engineering, Artificial Intelligence, or Applied Math with 12+ years of experience is sought, candidates with equivalent experience are encouraged to apply. A background in retrieval or multimodal research, evidenced by publications in leading conferences (CVPR, ICLR, ICCV, ECCV, KDD), is particularly preferred.
- Is this Senior Software Engineer role remote, and what are the location requirements?
- Yes, this role is remote, and the team is flexible with location, focusing on NA/EU time zones. NVIDIA is open to hiring candidates in any country where they have an office, accepting remote work arrangements.
- How does NVIDIA evaluate candidates for the Senior Software Engineer position?
- NVIDIA uses AI tools in its recruiting processes. Candidates are expected to demonstrate strong technical skills in agentic systems, retrieval research, and Python deep learning. Excellent communication skills are also essential, with an ability to share ideas through various platforms and a track record of mentoring junior engineers being a plus.
- What is the salary range for a Senior Software Engineer at NVIDIA?
- The base salary range for this position is $224,000 to $356,500 USD annually, determined by factors such as location, experience, and internal pay equity. Candidates may also be eligible for equity and benefits.
- What are the key responsibilities of a Senior Software Engineer on the Agentic Memory team at NVIDIA?
- Key responsibilities include designing novel benchmark tasks and evaluation methodologies for agentic memory systems, building synthetic dataset generation pipelines, and running experiments to diagnose and improve memory performance. You will also contribute to open-source evaluation harnesses and collaborate with other NVIDIA teams deploying agents.