Staff AI Inference Engineer — Hybrid, Multi-Cloud

Thomson Reuters Corp.; Eagan (MN); Hybrid; USD 127,000 - 237,000; Full time

Benefits offered by this job

Hybrid Work Model

Career Development

Industry Benefits

Job summary

Thomson Reuters Corp. seeks a Staff Inference Engineer to productionize and optimize AI/LLM workloads across AWS, Azure, GCP, and OCI.

You’ll collaborate with product, data science, and platform teams to onboard new research models into production while ensuring enterprise reliability and scalable performance. The role focuses on high-performance inference, latency reduction, and robust APIs integrated with Snowflake and OpenSearch vector search.

Qualifications

• 7+ years of relevant experience.
• Strong understanding of ML/LLM fundamentals and inference optimization techniques.
• Hands-on experience with GPU programming (CUDA preferred), inference runtimes (TensorRT, ONNX Runtime), and deep learning frameworks (PyTorch/TensorFlow).
• Proficiency in Python and at least one systems language (C++ strongly preferred for performance-critical inference paths).
• Experience deploying AI workloads to AWS/GCP/Azure and Kubernetes.

Responsibilities

• Productionize, optimize, and scale AI/LLM workloads across multi-cloud environments.
• Deploy inference workloads on GPUs and Kubernetes clusters.
• Implement routing, monitoring, and governance for enterprise AI services.
• Collaborate with Platform Engineering to align workloads with cloud-native patterns.

Skills

ML/LLM fundamentals

Inference optimization

GPU programming

Python

C++

Cloud deployments

Kubernetes

Tools

TensorRT

ONNX Runtime

PyTorch

CUDA

Job description

Thomson Reuters Corp. seeks a Staff Inference Engineer to productionize and optimize AI/LLM workloads across AWS, Azure, GCP, and OCI.

You’ll collaborate with product, data science, and platform teams to onboard new research models into production while ensuring enterprise reliability and scalable performance. The role focuses on high-performance inference, latency reduction, and robust APIs integrated with Snowflake and OpenSearch vector search.