AI Infrastructure Engineer - Hybrid, Impact & Innovation

Propio; Overland Park (KS); Hybrid; USD 140,000 - 200,000; Full time

Job summary

Propio is seeking an AI Infrastructure Engineer in Overland Park, hybrid. You will design, build, and operate AWS-based, GPU-accelerated inference and streaming serving platforms for LLMs, ASR, and multimodal models, while supporting research training environments and ML/LLMOps capabilities.

You'll collaborate with researchers and edge teams to enable scalable, low-latency workloads and implement secure, observable infrastructure.

Qualifications

• 3+ years building AI/ML infrastructure, inference platforms, or distributed systems in production.
• Hands-on AWS experience with EKS, EC2 GPU workloads, ECR, S3, IAM/KMS, VPC networking, CloudWatch and/or OpenTelemetry.
• Hands-on with at least one inference stack (vLLM, SGLang, TensorRT-LLM, Triton, KServe, or Ray Serve).
• Experience operating ML/LLM systems in production, including model serving, autoscaling, monitoring, incident response, and performance benchmarking.
• Familiarity with GPU infra and at least one serving stack (vLLM, SGLang, TensorRT-LLM, or Triton).
• Working understanding of LLM Ops practices, including evaluation, observability and tracing, cost control, and versioning.

Responsibilities

• Real-time inference systems: design, deploy, and operate low-latency streaming inference on AWS for LLMs and multimodal models.
• Support research training environments: reproducible containers, GPU job scheduling, distributed execution, experiment tracking.
• Build ML/LLMOps pipelines: registries, versioning, automated evaluation gates, deployments, canary and rollback workflows.
• Develop Edge AI workflows: model optimization, packaging, validation, deployment for edge targets.
• Ensure reliability and security: capacity planning, incident response, disaster recovery, IAM/KMS, private networking.

Skills

AI/ML infrastructure experience

AWS production experience

Inference stack knowledge

LLMOps practices understanding

GPU infrastructure familiarity

Production systems monitoring

Tools

vLLM

SGLang

TensorRT-LLM

Triton

KServe

Ray Serve

Megatron-LM

Slurm

SageMaker

Job description

Propio is seeking an AI Infrastructure Engineer in Overland Park, hybrid. You will design, build, and operate AWS-based, GPU-accelerated inference and streaming serving platforms for LLMs, ASR, and multimodal models, while supporting research training environments and ML/LLMOps capabilities.

You'll collaborate with researchers and edge teams to enable scalable, low-latency workloads and implement secure, observable infrastructure.