Neural Network Optimization Engineer

Summary

Join Untether AI, a rapidly growing Toronto-based startup, as a Neural Network Optimization Engineer and contribute to designing, developing, and verifying software that interacts with our chip, collaborating with hardware engineers and fellow software engineers.

Requirements

• Computer Science, engineering, or related degree
• At least 5 years of software development experience, specifically in AI
• Knowledge of Neural Network basic operator algorithms - Convolutions, Transformers, RNNs
• Experience with end to end software development, specifically data structures and algorithms, experience with software architecture patterns, etc
• Experience working in cross-functional teams
• Strong bias for teamwork and effective problem solving
• Experience with tuning and optimizing code and Neural Networks for high performance
• Strong communication skill and a background in program / project management
• Superior problem solving skills, both technical and interpersonal

Responsibilities

• Use and advance our products in the development and delivery of leading edge customer neural networks and applications
• Understand and evaluate neural network performance at a chip, system and application level through performance profiling and benchmarking
• Identify/diagnose challenges in using our products for specific use cases and define and develop projects to resolve them
• Engage with the Customer Neworks Lead on any escalations to the software and hardware team
• Actively engage with customers to ensure they feel supported by Untether AI post sale and delivery of the product
• Partner with the Products team to ensure they are up to date on client experiences and their feedback so that interactions with customers appear seamless
• Management of program / project teams to deliver Neural Network Model Garden Models including the identification, design and implementation of C++ low-level flexible programs (kernels) for various neural net operations
• When required development of complexed kernels and compiler strategies to address the network requirements
• Communicate performance optimization ideas both to compiler/kernel engineers and to architects working on future product generations

Benefits

• 20 vacation days
• Strong health and extended health benefits
• Unlimited sick days
• Stock options