NVIDIA's GPUs are at the core of modern AI infrastructure, from training large‑scale models to running inference in production. That position depends on software as much as hardware, and compiler engineering is a big part of what makes it work.
What You'll Be Doing
- Help trailblaze company efforts in applying AI within conventional compilation pipelines.
- Design and implement AI‑based technology addressing core problems of low‑level GPU programming.
- Build training pipelines for supervised fine‑tuning and reinforcement learning (RL/RLHF‑style or policy optimization variants).
- Define model inputs/outputs over compiler low level representations.
- Develop evaluation frameworks to measure code quality, runtime, compile‑time overhead, and correctness.
- Intelligent (domain‑task based) prompt engineering.
- Collaborate with compiler engineers to integrate learned policies into production toolchains.
- Prototype and iterate on model architectures, prompts, and fine‑tuning strategies for scheduling and allocation tasks.
- Create datasets from compiler traces, optimization passes, and target‑specific performance signals.
- Apply RL techniques to optimize for downstream objectives (performance, spill reduction, instruction‑level parallelism, etc.) and run rigorous experiments, ablations, and benchmarking across workloads and hardware targets.
What We Need To See
- M.S./Ph.D. degree in Computer Engineering, Computer Science related technical field (or equivalent experience).
- 5+ years of experience building AI/ML systems.
- Strong software engineering skills in Python and at least one systems language (C++ preferred).
- Hands‑on experience training/fine‑tuning large models (Transformers, PEFT/LoRA, distributed training).
- Solid understanding of machine learning fundamentals and experimentation best practices.
- Experience with reinforcement learning (e.g., policy gradients, actor‑critic, offline RL, bandit‑style optimization).
- Knowledge of prompt‑engineering techniques.
- Ability to work across research and engineering, from prototype to production.
Ways To Stand Out From The Crowd
- Distributed training/inference at scale.
- Experience working with the NVIDIA NeMo framework.
- Understanding of GPU performance, experience with benchmarking suites and performance profiling tools.
- Formal methods or static analysis familiarity for correctness guarantees.
- CUDA programming experience.
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 152,000 USD - 241,500 USD.
You will also be eligible for equity and benefits.
Equal Opportunity Employer
NVIDIA is committed to fostering a diverse work environment and is proud to be an equal opportunity employer. We do not discriminate 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.