Senior Inference Engineer - Ai

Thomson Reuters Corporation

Base: $110,000 - $204,200 usd (us); $100,000 - $14...
Hybrid
5+ years relevant experience
Gpu programming cuda preferred
Inference runtimes tensorrt onnx runtime
This role focuses on productionizing, optimizing, and scaling AI and LLM workloads to power Thomson Reuters' AI-driven products across a multi-cloud footprint

Job Summary

  • This role focuses on productionizing, optimizing, and scaling AI and LLM workloads to power Thomson Reuters' AI-driven products across a multi-cloud footprint.
  • The successful candidate will collaborate with platform teams to enhance capacity forecasting and onboard new research models into production while ensuring strict enterprise reliability.
  • Thomson Reuters offers a comprehensive benefits package including flexible vacation, mental health days, tuition reimbursement, and a competitive base salary range.

Matching Summary

This role focuses on productionizing, optimizing, and scaling AI and LLM workloads to power Thomson Reuters' AI-driven products across a multi-cloud footprint.

Salary

Base: $110,000 - $204,200 USD (US); $100,000 - $145,000 CAD (Ontario); Bonus: Eligible for Annual Bonus; Benefits: Comprehensive health, dental, vision, 401k match, tuition reimbursement

Skills & Requirements

Must-have

  • 5+ years relevant experience
  • GPU programming CUDA preferred
  • Inference runtimes TensorRT ONNX Runtime
  • Python and C++ proficiency
  • AWS GCP Azure Kubernetes deployment

Nice-to-have

  • Vector search systems OpenSearch
  • Distributed systems microservices knowledge
  • CI/CD and cloud native architecture
  • Retrieval augmented generation pipelines

Key Requirements

  • 5+ years of relevant experience
  • Strong understanding of ML/LLM fundamentals
  • Hands-on experience with GPU programming
  • Proficiency in Python and C++
  • Experience deploying AI workloads to AWS/GCP/Azure

Work Rights

Not specified

Tailored Resume

Cover Letter