Thomson Reuters
Senior Inference Engineer - AI
$110K–$204K
United States of America, Eagan, Minnesota +1 · Hybrid · Senior · Full-time · Posted Sep 22, 2026
- Location
- United States of America, Eagan, Minnesota
Canada, Toronto, Ontario - Experience
- 5+ years of relevant experience
About the job
Productionize, optimize, and scale AI and LLM inference workloads across cloud and Kubernetes environments for reliable integration into Thomson Reuters products and services.
What you'll do
- Optimize and deploy ML/LLM inference workloads, including GPU performance tuning, latency reduction, and scaling.
- Build production APIs, containerized inference pipelines, and routing, failover, monitoring, and governance capabilities.
- Collaborate with platform, cloud, data, product, and AI teams to onboard models and ensure reliable, compliant infrastructure.
What they ask for
- Strong understanding of ML/LLM fundamentals and inference optimization techniques.
- Hands-on experience with GPU programming, inference runtimes, and deep learning frameworks.
- Proficiency in Python and at least one systems language.
- Experience deploying AI workloads to AWS/GCP/Azure and Kubernetes.
Nice to have
- CUDA; C++ strongly preferred for performance-critical inference paths.
- Familiarity with vector search systems and retrieval augmented generation pipelines.
Pay
$110,000 USD - $204,200 USD (base salary); $100,000 CAD - $145,000 CAD (base salary)
Tools
AWS, Azure, GCP, OCI, Kubernetes, CUDA, TensorRT, ONNX Runtime
AI focus
Productionize, optimize, and scale classical ML and generative AI inference; tune models and GPU workloads; onboard research models; support routing, monitoring, governance, and drift detection.
Model-written summary · the original posting is authoritative