Senior AI Platform Engineer

Qualcomm • San Diego, CA

81d • $111,300 - $166,900 • Hybrid

About The Position

We are seeking a Senior AI Platforms Engineer to design, build, and operate the infrastructure that powers large-scale AI and ML workloads, with a strong focus on LLM hosting and serving at scale. This role requires deep expertise in Kubernetes, multi-cloud environments, and observability systems, as well as experience with agentic workflow orchestration (e.g., n8n) in production environments. You will collaborate with global teams to deliver secure, reliable, and cost-efficient AI platforms.

Requirements

• 5-7 years of experience in platform engineering, MLOps, or SRE roles.
• Strong hands-on experience with Kubernetes (production-grade deployments, autoscaling, GPU scheduling).
• Cloud platforms: AWS (Bedrock, SageMaker), plus GCP and/or Azure.
• Python and scripting languages (Bash, PowerShell).
• Linux systems administration.
• Proven experience hosting and serving LLMs at scale in production environments.
• Expertise in observability: Elasticsearch, Prometheus, Grafana, OpenTelemetry.
• Familiarity with agentic workflow systems (e.g., n8n) and scaling them for enterprise use.
• Strong understanding of networking, security, and IAM in cloud-native environments.
• Excellent communication skills and ability to work with global teams.

Nice To Haves

• Experience with model serving frameworks (vLLM, Triton, KServe, Ray Serve).
• Knowledge of vector databases (Elasticsearch vector, Milvus, Pinecone) for RAG workflows.
• Familiarity with service mesh (Istio/Linkerd), policy-as-code (OPA/Gatekeeper).
• GPU optimization for inference workloads.
• Certifications: AWS Solutions Architect or ML Specialty, CKA/CKAD.

Responsibilities

• Deploy and manage large language models (LLMs) at scale using AWS Bedrock, GCP Vertex, Azure AI Foundry and Kubernetes-based solutions.
• Optimize inference performance for throughput, latency, and cost efficiency.
• Build and maintain Kubernetes clusters for AI workloads with GPU scheduling, autoscaling, and high availability.
• Model and deploy auto scaling applications and APIs to existing Kubernetes clusters.
• Implement CI/CD pipelines and Infrastructure as Code (Terraform, Helm).
• Design and implement observability stacks for large-scale systems, including metrics, logs, and traces.
• Manage large-scale search systems built on elasticsearch powering hybrid-search solutions.
• Deploy and scale agentic workflow orchestration systems (e.g., n8n) for AI-driven automation.
• Ensure reliability, security, and performance of workflow execution at scale.
• Operate across AWS, GCP, and Azure, leveraging managed AI services and GPU infrastructure.
• Work closely with globally distributed teams; provide documentation, mentorship, and participate in on-call rotations.

Benefits

• Competitive annual discretionary bonus program.
• Opportunity for annual RSU grants.
• Comprehensive benefits package designed to support success at work, at home, and at play.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Industry: Computer and Electronic Product Manufacturing
• Education Level: Bachelor's degree
• Number of Employees: 5,001-10,000 employees