Embedded Platform Engineer: Kubernetes & AI Infra

Broadcom Inc.; New Mexico; On-site; USD 111,000 - 177,000; Full time

Benefits offered by this job

Medical, dental and vision

401(k) with company matching

Employee Stock Purchase Program (ESPP)

Paid holidays and vacation

Job summary

Broadcom Inc. seeks a hands-on Forward Deployed Engineer (Staff) specializing in Kubernetes, platform modernization, and large-scale stateful workload migrations.

You will embed with enterprise client teams across the full lifecycle, from architecture and replatforming to live field troubleshooting and production rollout. You will write production code in the field, build prototype integrations, and feed back to ISG to prioritize platform features.

Qualifications

• Bachelor's degree preferred or equivalent experience.
• Proven track record in enterprise-grade Kubernetes deployments.
• Experience migrating large stateful workloads to cloud-native platforms.
• Hands-on experience with GPU-accelerated AI workloads and model serving.
• Strong collaboration with product and engineering teams.

Responsibilities

• Embed with enterprise client teams to drive end-to-end migration and deployment.
• Architect, deploy, and optimize VKS clusters across hybrid environments.
• Troubleshoot production issues with networking, storage, and GPU acceleration.
• Translate field feedback into core engineering requirements and roadmap items.

Skills

Kubernetes

Platform modernization

AI infrastructure

Stateful workload migration

In-field engineering

Docker/containers

Terraform

GitOps

Distributed systems

GPU/NPU workloads

Education

Bachelor's degree

Tools

Apache Kafka

RabbitMQ

Redis

Oracle Coherence

Hazelcast

Milvus

Qdrant

Pgvector

Ray

Triton Inference Server

vLLM

Job description

Broadcom Inc. seeks a hands-on Forward Deployed Engineer (Staff) specializing in Kubernetes, platform modernization, and large-scale stateful workload migrations.

You will embed with enterprise client teams across the full lifecycle, from architecture and replatforming to live field troubleshooting and production rollout. You will write production code in the field, build prototype integrations, and feed back to ISG to prioritize platform features.