Senior AI Inference Architect

Thomson Reuters; Eagan (MN); Hybrid; USD 110,000 - 204,200; Full time

Benefits offered by this job

Hybrid Work Model

Mental Health Days

Job summary

Thomson Reuters seeks a Senior Inference Engineer, AI to advance AI/LLM workloads across multi-cloud platforms, collaborating with platform teams and product units to productionize models and scale inference services.

You will optimize performance with GPU techniques, deploy on Kubernetes across AWS/Azure/GCP, and ensure reliable APIs for TR products while aligning with enterprise AI standards.

Qualifications

• 5+ years of relevant experience.
• Strong ML/LLM fundamentals and inference optimization techniques.
• Hands-on GPU programming (CUDA) and inference runtimes (TensorRT, ONNX Runtime).
• Proficiency in Python and at least one systems language (C++ strongly preferred).
• Experience deploying AI workloads to AWS/GCP/Azure and Kubernetes.
• Familiarity with vector search systems (OpenSearch vectors) and retrieval augmented generation pipelines.
• Knowledge of distributed systems, microservices, CI/CD, and cloud native architecture.

Responsibilities

• Productionize, optimize, and scale AI and LLM workloads across multi-cloud environments.
• Deploy GPU-accelerated inference on Kubernetes clusters with high reliability.
• Implement routing and failover for OpenAI/Anthropic/Vertex AI traffic.
• Integrate models into production-grade APIs for TR products.
• Profile performance, identify bottlenecks, and optimize compute usage.
• Collaborate with platform engineering to align with cloud-native patterns.
• Develop containerized inference pipelines with Kubernetes for large-scale workloads.

Skills

ML fundamentals

LLM understanding

CUDA

TensorRT

ONNX Runtime

Python

C++

AWS/GCP/Azure

Kubernetes

OpenSearch vectors

Tools

TensorRT

ONNX Runtime

CUDA

Job description

Thomson Reuters seeks a Senior Inference Engineer, AI to advance AI/LLM workloads across multi-cloud platforms, collaborating with platform teams and product units to productionize models and scale inference services.

You will optimize performance with GPU techniques, deploy on Kubernetes across AWS/Azure/GCP, and ensure reliable APIs for TR products while aligning with enterprise AI standards.