Join NVIDIA's Autonomous Vehicle Evaluation (AV Eval) team as a senior software engineer where you will design and build next-generation evaluation pipelines using large language models (LLMs), vision-language models (VLMs), and multimodal systems. Your day-to-day involves developing agentic workflows to assess complex driving scenarios, defining methodologies for evaluating the accuracy of these evaluators, and building robust frameworks for data calibration and model versioning. You will work closely with cross-functional teams to transition from rule-based to learned evaluation methods, ensuring that autonomous vehicle software meets stringent safety standards before release. Ideal candidates have hands-on experience in ML production systems, strong Python and C++ skills, familiarity with large-scale data processing tools like Spark or Dask, and a background in autonomous driving or robotics. This role offers high ownership and visibility within NVIDIA’s AV leadership, contributing to the development of groundbreaking technologies that aim to revolutionize road safety globally.
Skills
Python
PyTorch
JAX
LLMs
VLMs
C++
Spark
Dask
LangChain
DSPy
CrewAI
CI/CD
GPU
Video understanding models
Multi-modal evaluation
Agentic AI frameworks
Large-scale data processing
Evaluation methodology
Precision/recall
Inter-rater reliability
Calibration
Annotation pipelines
What you'll do
Design and build learned evaluation pipelines using LLMs and VLMs for assessing driving behavior.
Develop agentic workflows that integrate model inference, retrieval, and reasoning for complex scenario evaluations.
Define methodologies to evaluate the accuracy of learned evaluators in autonomous vehicle systems.
Build frameworks for golden-set creation and calibration loops to ensure reliable learned metrics.
Contribute to transitioning from rule-based to machine learning-driven evaluation methods in AV systems.
What we're looking for
Hands-on experience building LLM/VLM-based pipelines including fine-tuning and prompt engineering.
Track record of shipping machine learning systems to production with strong software engineering fundamentals.
Expertise in evaluation methodology, large-scale data processing, and Python programming.
Experience with autonomous driving, robotics, or safety-critical domains and familiarity with driving behavior taxonomies.
Knowledge of video understanding models, multi-modal evaluation, and agentic AI frameworks.
Comfortable working with GPU-based training workflows and deep learning libraries like PyTorch or JAX.
Market check
Salary context
This
$184,000–$287,500
range sits above
68%
of similar postings on FindRole.
Peer median band
$179,137–$261,300
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$194,937–$248,375
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
825 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 813 roles with salary data.