Responsibilities

• Design and implement scalable and performant systems to serve machine learning models
• Optimize training and inference performance of deep learning models
• Create and maintain feature pipelines, feature stores, model stores
• Monitor production models and setup retraining infrastructure to improve performance
• Optimize models for deployment on different hardware configurations
• Build frameworks to promote scalable and reproducible research
• Drive projects and lead new initiatives
• Facilitate discussions on code implementation, testing, software architecture best practices
• Actively engage with others on the team to resolve challenging design and coding issues
• Collaborate with stakeholders from different departments
• 
  

Qualifications

• A bachelor’s or a master’s degree in computer science, software engineering or equivalent
• 5+ years of experience building software for machine learning systems
• Strong understanding of machine learning and deep learning concepts
• Excellent programming and scripting skills
• Experience with building, validating, deploying, monitoring, and updating production models
• Experience with infrastructure and tooling for MLOps
• Strong problem-solving and analytical skills
• Excellent communication and collaboration skills
• Experience with machine learning frameworks such as TensorFlow, PyTorch, TensorRT, ONNX
• Experience with GPU programming using CUDA, OpenCL or similar libraries
• Experience optimizing inference performance (quantization, profiling, kernel/runtime tuning, serving engines)
• Experience with one or more of the following is an asset: distributed systems, multi-threaded programming, hardware/software interaction

Responsibilities

• Design and implement scalable and performant systems to serve machine learning models
• Optimize training and inference performance of deep learning models
• Create and maintain feature pipelines, feature stores, model stores
• Monitor production models and setup retraining infrastructure to improve performance
• Optimize models for deployment on different hardware configurations
• Build frameworks to promote scalable and reproducible research
• Drive projects and lead new initiatives
• Facilitate discussions on code implementation, testing, software architecture best practices
• Actively engage with others on the team to resolve challenging design and coding issues
• Collaborate with stakeholders from different departments
• 
  

Qualifications

• A bachelor’s or a master’s degree in computer science, software engineering or equivalent
• 5+ years of experience building software for machine learning systems
• Strong understanding of machine learning and deep learning concepts
• Excellent programming and scripting skills
• Experience with building, validating, deploying, monitoring, and updating production models
• Experience with infrastructure and tooling for MLOps
• Strong problem-solving and analytical skills
• Excellent communication and collaboration skills
• Experience with machine learning frameworks such as TensorFlow, PyTorch, TensorRT, ONNX
• Experience with GPU programming using CUDA, OpenCL or similar libraries
• Experience optimizing inference performance (quantization, profiling, kernel/runtime tuning, serving engines)
• Experience with one or more of the following is an asset: distributed systems, multi-threaded programming, hardware/software interaction