Senior System Software Engineer - Dynamo and Triton Inference Server
NVIDIASalary not specified
- Full Time
- Senior (5 to 8 years)
$130,000 – $180,000Compensation
Mid-level (3 to 4 years), Senior (5 to 8 years)Experience Level
InternshipJob Type
UnknownVisa
Artificial Intelligence, AI & Machine LearningIndustries
Requirements
Candidates should possess experience with ML systems and deep learning frameworks such as PyTorch, TensorFlow, or ONNX, and familiarity with common LLM architectures and inference optimization techniques like continuous batching and quantization. Prior experience deploying reliable, distributed, real-time model serving at scale is also required, along with optional understanding of GPU architectures or CUDA programming experience.
Responsibilities
The AI Inference Engineer will develop APIs for AI inference to be utilized by both internal and external customers, benchmark and address bottlenecks within the inference stack, improve the reliability and observability of systems, and respond to system outages. They will also explore novel research and implement LLM inference optimizations.
Skills
PyTorch
TensorFlow
ONNX
LLM architectures
Continuous batching
Quantization
Model serving
GPU architectures
CUDA
Perplexity AI
Advanced answer engine providing reliable information
About Perplexity AI
Perplexity AI provides an advanced answer engine that delivers accurate and reliable responses to user queries. The platform uses current sources to ensure the information is both precise and relevant. It caters to a wide audience, including individuals looking for quick answers and businesses needing detailed information. Unlike many competitors, Perplexity AI emphasizes high-quality, source-backed answers, making it a valuable resource for users seeking trustworthy data. The company's goal is to meet the increasing demand for immediate access to reliable information, generating revenue through subscription fees, advertising, and partnerships.
San Francisco, CaliforniaHeadquarters
2022Year Founded
$890MTotal Funding
LATE_VCCompany Stage
Data & Analytics, Consumer SoftwareIndustries
201-500Employees