Drive cutting-edge AI initiatives as a Lead AI Support Engineer at TR, focusing on high-performance inference optimization and effective deployment strategies. Collaborate with top-tier technology.
TR is seeking a knowledgeable engineer to lead the optimization of inference models. This hybrid role demands over three years of experience deploying AI workloads across cloud platforms. You will optimize LLMs, implement routing strategies, and monitor pipeline health while working closely with various teams across the organization.
Key Responsibilities:
• Optimize inference workloads with quantization and tuning
• Profile and improve GPU/CPU performance
• Develop and implement AI deployment strategies




• Work with platform teams on scalability and compliance
• Create efficient containerized solutions for AI services
Requirements:
• 3+ years of experience in ML/LLM model deployment
• Expertise in Python and C++ for critical inference tasks
• Familiarity with Kubernetes and cloud infrastructure
• Understanding of up-to-date AI architectures and networks
• Knowledge of industry compliance standards for AI workloads
Utilize your expertise in model optimization and cloud to enhance TR's AI offerings.
#J-18808-Ljbffr

📌 Lead AI Support Engineer at TR (Toronto)
🏢 Refinitiv
📍 Toronto