Senior Inference Engineer for AI at Thomson Reuters

Role description

Enhance AI capabilities as a Senior Inference Engineer with Thomson Reuters, where hybrid work enables flexibility. Collaborate with cross-functional teams to deploy and scale cutting-edge AI workloads.
In this influential role, you will be embedded within Platform Engineering and Enterprise AI Services, tasked with ensuring that AI and LLM workloads meet industry standards. Your 5+ years of experience and deep understanding of inference optimization will be vital for success.
Key Responsibilities:
• Implement scalable inference solutions on GPUs
• Optimize AI workloads for low latency
• Collaborate on cloud-native patterns across platforms
• Develop best practices in containerized deployments
• Ensure robust monitoring and observability of pipelines
Requirements:
• 5+ years in AI/ML environments
• Proficiency in GPU programming and CUDA
• Experience deploying models on Kubernetes
• Familiarity with deep learning runtimes
• Strong skills in Python and C++
Leverage your expertise to shape the future of AI infrastructure at Thomson Reuters.
#J-18808-Ljbffr