Sr. Principal Software Engineer

For a leader in the Manufacturing & Automotive space, this role leads work at the intersection of data, AI-enabled capabilities, and scalable technology delivery. You will collaborate across engineering, product, operations, and business stakeholders to translate complex requirements into practical technology solutions, influencing architecture, execution quality, and long-term technology capabilities in a manufacturing environment.

Location: Remote – US-based candidates only, no visa sponsorship available.

Responsibilities

• Optimize and deploy LLM inference pipelines
• Manage inference runtimes across various platforms
• Enhance model performance using techniques like quantization and kernel fusion
• Drive improvements in latency and throughput for production products
• Enable efficient deployment independent of external vendors
• Build expertise in key inference engines
• Adapt runtimes for constrained environments

Qualifications

• 5-7 years experience in ML inference performance optimization
• In-depth knowledge of GPU architecture and memory hierarchies
• Proficiency in CUDA and low-level performance tuning
• Experience deploying models in production environments
• Familiarity with inference engines like vLLM, TensorRT-LLM, llama.cpp, QAIRT
• Expertise in quantization techniques including INT8, INT4, FP4, FP8, AWQ, GPTQ
• A solid understanding of latency optimization strategies

Pay

$141,400 – $226,300 annually

Benefits

• Annual bonus opportunity
• Comprehensive insurance coverage including medical, dental, vision, life, and disability
• Paid time off and holidays
• Company contributions to RRSP
• Equity awards available for select roles
• Remote or hybrid work options based on position