AI Accelerator, Software Principal Engineer- Full-Stack

About the role

We are looking for an engineer with strong experience in PyTorch-based AI deployment, accelerated inference execution, and systems integration across software components. The role involves working on temporal and multi-modal workloads, optimizing execution on target platforms, and building infrastructure to run AI models reliably in production environments.

Responsibilities

• Deploy and validate different AI models across supported inference environments (local, on-prem, or edge/accelerated platforms), optimizing runtime performance and reliability.
• Develop and tune inference graph transformations, including torch.export-based graph workflows.
• Collaborate with platform and infrastructure teams to improve model execution efficiency on supported AI accelerators and compute environments.
• Integrate model inference pipelines into scalable services, including batching, streaming, and runtime orchestration.
• Build and maintain middleware and communication layers to support modular, scalable system integration.
• Support long-term platform development for end-to-end inference services and production readiness.

Requirements

• Relevant Technical Areas:
  • Temporal model architectures
  • Multi-frame or sequence embeddings (e.g., video/text sequences)
  • Attention-based models
  • Multi-modal workloads (e.g., text, imaging, and other feature modalities)
  • Automated labeling, evaluation, and validation workflows
  • CPU/runtime performance optimization for system components
  • Publish-subscribe middleware and distributed communication systems

Qualifications

• Bachelor's degree in Computer Science, Mathematics or a related technical field & 8 years of related experience; or Master's degree & 6 years
• Strong hands-on experience with PyTorch
• Experience deploying AI models to accelerated or constrained environments (e.g., edge, cloud GPU, or specialized accelerators)
• Familiarity with graph optimization and model-performance tuning
• Experience working with middleware, messaging, or distributed communication layers
• Good understanding of hardware/software interaction in AI systems
• Experience collaborating with hardware or platform partners

Skills

• Hands-on experience with PyTorch
• Experience deploying AI models to accelerated or constrained environments
• Familiarity with graph optimization and model-performance tuning
• Experience working with middleware, messaging, or distributed communication layers
• Good understanding of hardware/software interaction in AI systems
• Experience collaborating with hardware or platform partners

Benefits

• Premium medical insurance
• Dental insurance
• Vision insurance
• Income protection
• 401K retirement plan

Pay

• The full base pay range for this role is between $195,000 and $292,000.

Schedule

• Flexible work schedule
• 10+ paid holidays