AI Infrastructure Engineer

Propio is a communication services company focused on removing barriers and connecting people, communities, and opportunities. The AI Infrastructure Engineer will design, build, and operate AWS-based, GPU-accelerated inference and streaming platforms while supporting AI model training, ML/LLMOps, edge AI deployments, reliability, and security.

Responsibilities:

• Design, deploy, and operate low-latency streaming inference systems on AWS for LLM, ASR, TTS, and multimodal models. Optimize time to first token/audio, p95/p99 end-to-end latency, real-time factor, throughput, concurrency, GPU utilization, and cost per stream using technologies such as vLLM, SGLang, TensorRT-LLM, Triton, TensorRT
• Support and evolve the research team’s AWS-based training environment, including reproducible containers, GPU job scheduling, distributed job execution, checkpoint and resume capabilities, experiment tracking, model and data artifact access, and researcher self-service. Enable workloads using FSDP, DeepSpeed, Megatron-LM, Slurm, EKS, or SageMaker
• Build model and artifact registries, lineage and versioning, automated evaluation gates, deployment pipelines, shadow and canary releases, rollback workflows, runtime and configuration management, and production observability
• Partner with researchers and device and embedded teams to build repeatable model optimization, packaging, validation, and deployment workflows for resource-constrained edge targets. Support model export and compilation, post-training quantization, runtime integration
• Own capacity planning, production readiness, incident response, disaster recovery, and the secure operation of the AI platform. Apply least-privilege IAM, KMS encryption, private networking, secrets management