Principal Software Engineer
Core
Design and implement complex inferencing capabilities for state-of-the-art deep learning models and build robust frameworks supporting experimentation and production use-cases.
Role type
Principal Software Engineer (AI Infrastructure & Inference)
Builds
AI inference frameworks, internal tools for the AI lifecycle (experiment tracking, model versioning, performance monitoring), and production-grade deep learning applications.
Domain
Artificial Intelligence, Deep Learning, High-Performance Computing
Deliverable
production ML models
Required skills
Deep learning frameworks (PyTorch, OnnxRuntime, Tensorflow, vLLM, TensorRT-LLM), end-to-end system design, low-level GPU architecture, kernel programming, model quantization, Docker, Kubernetes, high-performance application development, technical leadership, mentoring
Preferred skills
MLOps familiarity, open-source project contribution, community building, inclusive environment fostering
Technologies
PyTorch, OnnxRuntime, Tensorflow, vLLM, TensorRT-LLM, C, C++, C#, Java, JavaScript, Python, Docker, Kubernetes
Responsibilities
Engage with partners to understand and design inferencing capabilities; develop reusable frameworks for experimentation and production; optimize inference performance and cost on cutting-edge hardware; develop internal tools for the AI lifecycle; mentor early-in-profession engineers.
Seniority
Principal, hands-on IC with strategic impact and mentorship
