Senior Software Engineer, AI (C#, Cloud)
Core
Optimize LLMs and ML models for high-performance inference, deploy and scale workloads on cloud GPUs, and integrate models into production APIs for enterprise workflows.
Role type
Senior IC Software Engineer (AI/ML Inference & Cloud)
Builds
Production-grade AI inference pipelines, containerized workloads, and optimized APIs for Thomson Reuters products.
Domain
Enterprise Legal/Tax/Accounting + Cloud AI Infrastructure
Deliverable
production ML models
Required skills
LLM/ML inference optimization, C#, Python, GPU programming (CUDA), Kubernetes, AWS/GCP/Azure, deep learning frameworks (PyTorch/TensorFlow), inference runtimes (TensorRT/ONNX Runtime), distributed systems, microservices, CI/CD, vector search, AI network architectures (CNNs/Transformers/Diffusion), SW/HW co-design
Preferred skills
Model compression, hardware-aware optimizations, GPU fleet management, regulated environment experience
Technologies
C#, Python, CUDA, Kubernetes, AWS, Azure, GCP, OCI, TensorRT, ONNX Runtime, PyTorch, TensorFlow, OpenSearch
Responsibilities
Optimize LLMs using quantization, pruning, and distillation; Deploy and scale inference on GPUs across cloud providers; Implement routing/failover for AI traffic; Integrate models into production APIs; Profile and optimize compute utilization; Build containerized inference pipelines; Ensure compliance with AI governance standards; Collaborate on capacity forecasting and model onboarding.
Seniority
Senior, hands-on IC