Thomson Reuters is seeking a Senior Inference Engineer, AI to productionize, optimize, and scale AI/LLM workloads powering TR’s AI-driven products.
The role focuses on deploying across multi-cloud environments (AWS, Azure, GCP) and on‑prem Kubernetes clusters, reducing latency and ensuring enterprise reliability, with collaboration across Platform Engineering, Data Science, and Product teams.
Strong CUDA, TensorRT/ONNX Runtime, PyTorch or TensorFlow experience is required.
#J-18808-LjbffrSenior AI Inference Engineer - Scalable LLM Production in eagan at Unknown Company
This position is listed as full time and onsite.