Advance your skills as a Machine Learning Inference Engineer at Thomson Reuters, specializing in AI and deep learning in a hybrid environment.
This role involves optimizing large-scale ML models for advanced inference capabilities while deploying workloads on infrastructure across platforms like AWS and GCP. You'll also innovate routing strategies and ensure compliance with the latest AI governance standards. Collaboration will be key as you work across teams to enhance model integrations and optimize performance.
Key Responsibilities:
• Enhance LLM and machine learning model efficiency
• Deploy and manage AI workloads on cloud platforms
• Build containerized inference pipelines
• Optimize compute utilization and identify bottlenecks
• Collaborate for enhanced AI capacity forecasting
Requirements:
• 3+ years experience deploying ML models in production
• Expertise in GPU programming and inference runtimes
• Solid knowledge of cloud-native architecture and CI/CD practices
• Familiarity with AI model architectures like transformers
• Proficient in Python and one systems language
Contribute to innovative AI solutions that impact the world at Thomson Reuters.
#J-18808-Ljbffr