Senior DL Software Engineer, Model Optimization and Edge Deployment - Autonomous Vehicles at NVIDIA

**Who this is for** This role is for a seasoned Deep Learning Software Engineer focused on optimizing large language and visual language models for real-time pe

Work type: onsite

Location: US, CA, Santa Clara

Type: Full-time

Summary

**Who this is for** This role is for a seasoned Deep Learning Software Engineer focused on optimizing large language and visual language models for real-time performance in autonomous vehicles. You will be crucial in bridging the gap between advanced AI research and practical, on-edge deployment. **Key highlights** You will be responsible for developing and implementing cutting-edge model optimization techniques to ensure complex AI models run efficiently and reliably on autonomous vehicle hardware. This involves deep profiling, compression, and scaling DL models across NVIDIA's edge architectures. **You might be a good fit if you...** - Have expert-level proficiency in ML frameworks like PyTorch or JAX, and experience with LLM/VLM inference stacks. - Possess a strong track record of training, deploying, or optimizing large-scale DL models in production. - Have deep familiarity with NVIDIA's DL SDKs, particularly TensorRT and CUDA, and understand GPU architecture. - Are passionate about making self-driving vehicles a reality and are ready to contribute to this impactful technology.

Job Description

NVIDIA is at the forefront of the AI revolution, specifically in the constantly evolving field of Embodied AI. We are seeking a high-caliber Deep Learning Engineer to bridge the gap between cutting-edge multimodal architectures and real-time robotic execution for autonomous vehicles. In this role, you will design and implement SOTA algorithms to make LLM/VLM fast, lean, and reliable enough to power an end-to-end driving stack. You won’t just be "running" models; you will be re-architecting them for the edge, ensuring that models capable of complex scene reasoning can operate within the strict latency and safety constraints of an AV compute platform.

What You’ll Be Doing:

• Develop SOTA model optimization techniques, such as speculative decoding with block diffusion, KV cache streaming, and Prefill–Decode separation, etc. to boost E2E model performance for production deployments.

• Implement advanced compression techniques including Quantization (FP4/FP8), pruning, and knowledge distillation to minimize model footprints without compromising safety-critical accuracy.

• Design high-performance optimization strategies for inference, including automated model sharding (tensor/sequence parallelism) and the development of efficient attention kernels optimized for KV-caching.

• Conduct deep, layer-by-layer model profiling to identify compute and memory bottlenecks, driving targeted optimizations for real-time execution.

• Leverage the PyTorch ecosystem to extract standardized model graph representations and automate deployment pipelines for TensorRT conversion.

• Scale DL model performance across diverse NVIDIA edge architectures, maximizing the throughput of specialized accelerators on the road.

• Architect the software interface to seamlessly integrate and interact with large-scale models within a high-performance C++ production environment.

• Partner with research, TensorRT, and Cosmos teams to translate breakthrough innovations into shipping product solutions.

• PhD with 4+ years, MS with 6+ years, or BS (or equivalent experience) with 8+ years of relevant experience in Computer Science, Computer Engineering, or a related technical field.

• Expert-level proficiency in PyTorch, JAX, or similar machine learning frameworks.

• Sophisticated proficiency with modern LLM/VLM inference stacks, such as vLLM, TensorRT-LLM and SGLang.

• A proven track record of training, deploying, or optimizing large-scale DL models in production environments.

• Deep familiarity with NVIDIA’s deep learning SDKs, specifically TensorRT and CUDA.

• Strong understanding of GPU architecture, the compilation stack, and the ability to debug end-to-end performance across the hardware/software boundary.

• Deep experience with LLM, VLM, and VLA model optimization, specifically tailored for real-time robotic control, embodied AI, and autonomous decision-making.

• Proven track record of implementing low-bit inference

• Prior experience writing custom high-performance kernels using CUDA, Triton, or CUTLASS to accelerate non-standard neural network layers and specialized attention mechanisms.

• Active contributions to open-source inference and optimization libraries such as vLLM, SGLang and TensorRT-LLM.

• Thorough understanding of the unique constraints of real-time robotics, including safety-critical determinism, hardware-in-the-loop (HIL) testing, and ultra-low latency requirements.

Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 184,000 USD - 287,500 USD for Level 4, and 224,000 USD - 356,500 USD for Level 5.

You will also be eligible for equity and [benefits](https://www.nvidia.com/en-us/benefits/).

Applications for this job will be accepted at least until April 25, 2026.

This posting is for an existing vacancy. 

NVIDIA uses AI tools in its recruiting processes.

NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

View this job on nocollar jobs