Senior Deep Learning Software Engineer, Inference

Nvidia seeks a Senior Deep Learning Software Engineer, Inference for a full-time role based in 5 Locations. Candidates passionate about production-grade neural network deployment will find this Senior Deep Learning Software Engineer, Inference opening a strong match for advancing efficient model execution software near 5 Locations.

About This Position

This full-time Senior Deep Learning Software Engineer, Inference role at Nvidia in 5 Locations centers on creating robust software that transforms trained models into fast, reliable inference systems ready for real-world use. You will work as part of a collaborative engineering team that prioritizes clean architecture, measurable performance gains, and seamless integration of next-generation deep learning techniques. The position offers the chance to own critical components of declaration-to-runtime pipelines while contributing to high-impact projects that demand both depth in machine learning systems and excellence in production software practices. Job seekers looking for Senior Deep Learning Software Engineer, Inference jobs in 5 Locations or Nvidia careers involving inference will recognize the blend of technical rigor and hands-on problem solving this role requires.

Day-to-Day Responsibilities

• Architect and implement high-performance software layers that accelerate neural network inference across varied hardware targets.
• Profile end-to-end execution paths, isolate bottlenecks, and deliver targeted optimizations that improve latency and throughput.
• Integrate modern deep learning frameworks and intermediate representations into custom runtime environments.
• Collaborate daily with researchers and platform engineers to translate novel model designs into efficient, maintainable codebases.
• Develop thorough unit, integration, and performance test suites to guarantee reliability under production loads.
• Document designs, review peer contributions, and mentor junior engineers on best practices for inference-focused development.

Qualifications

• Bachelor’s or master’s degree in computer science, computer engineering, or a closely related discipline.
• Significant professional experience building and optimizing deep learning software, with clear emphasis on inference runtimes.
• Expert-level proficiency in C++ and Python for systems-level and application-level coding.
• Hands-on familiarity with parallel programming models and accelerator interfaces commonly used for high-speed model execution.
• Working knowledge of mainstream machine learning frameworks and their deployment pathways.
• Demonstrated skill in diagnosing complex performance issues and applying data-driven improvements.
• Strong communication abilities and a track record of thriving inside multi-disciplinary software teams.

Working at Nvidia

Nvidia is hiring for this role and offers a supportive team environment where skilled engineers can deepen their expertise and tackle meaningful technical challenges side by side.

Ready to Apply?

To apply, complete your application directly on this page, or you'll be redirected to the employer's application platform to finish submitting there.