Senior AI Platform Engineer
Core
Define and deliver infrastructure strategy for IQVIA's Large Language Model (LLM) programmes, transforming research innovations into secure, scalable, production-ready AI solutions.
Role type
Senior IC AI Platform Engineer (LLM Infrastructure)
Builds
High-performance compute environments, model lifecycle platforms, and knowledge graph infrastructure for healthcare AI systems.
Domain
Healthcare + Large Language Models (LLM) + Distributed Computing
Deliverable
production ML models
Required skills
LLM architecture design, GPU infrastructure management, distributed training strategies, model optimization (quantization, mixed precision), AWS cloud services, Kubernetes/Slurm/Ray orchestration, vendor selection for AI compute
Preferred skills
Experience bridging research and production environments, leading cross-functional technical initiatives
Technologies
PyTorch, CUDA, cuDNN, NCCL, vLLM, TensorRT-LLM, NVIDIA NIM, SGLang, NVIDIA Nsight, DCGM, AWS, Kubernetes, Ray, Slurm
Responsibilities
Own the AI platform and infrastructure roadmap; design and deliver high-performance compute environments; optimize LLM training and inference workloads; establish model and data lifecycle capabilities; lead knowledge graph infrastructure evolution; serve as primary technical coordination point; provide technical leadership for vendor selection; define platform engineering standards and mentor engineers
Seniority
Senior, hands-on IC with technical leadership
