Senior AI Platform Engineer – Model Serving & Ops

Cisco Systems, Inc; San Jose (CA); Vor Ort; USD 168.000 - 245.000; Vollzeit

Benefits dieser Stelle

RSUs

401(k) with match

Parental leave

Health insurance

Zusammenfassung

Cisco Systems, Inc is seeking a Senior Software Engineer to guide model serving, runtime tuning, and accelerator optimization within the Foundational Model Service. You will lead incident response, improve reliability, and automate remediation while collaborating across design, product, and engineering to advance customer solutions and production readiness.

The role requires production experience with AI infrastructure, strong knowledge of LLM/embedding internals, and hands-on work with

Qualifikationen

• 7+ years of systems, platform, or software engineering experience.
• Production background operating AI infrastructure.
• Understanding of LLM, SLM, embedding, and reranker internals.
• Experience serving models on inference runtimes (vLLM, NVIDIA NIM, Triton).
• Proven ability to build services around models (APIs, gateways, tooling).
• Depth in evaluating and benchmarking models for release decisions.

Aufgaben

• Contribute to model serving direction and runtime tuning.
• Develop platform services, APIs, gateways, and tooling around model inference.
• Lead on-call response, postmortems, and durable reliability improvements.
• Mentor engineers and raise technical standards across teams.
• Coordinate with product, design, and engineering to plan capacity and milestones.

Kenntnisse

Kubernetes

Python

Go

CI/CD

Terraform

Ansible

Prometheus

Grafana

GitOps

Helm

ArgoCD

NVIDIA NIM

vLLM

Triton

PyTorch

HuggingFace

LoRA

QLoRA

QLoRA

Ausbildung

Bachelor's degree in Computer Science, Information Systems, or related field

Tools

Envoy

NGINX

APISIX

Jobbeschreibung

Cisco Systems, Inc is seeking a Senior Software Engineer to guide model serving, runtime tuning, and accelerator optimization within the Foundational Model Service. You will lead incident response, improve reliability, and automate remediation while collaborating across design, product, and engineering to advance customer solutions and production readiness.

The role requires production experience with AI infrastructure, strong knowledge of LLM/embedding internals, and hands-on work with