Staff AI Infra Engineer: Scale GPU AI Platforms

Seekr; San Francisco (CA); Hybrid; USD 180,000 - 260,000; Full time

Benefits offered by this job

Equity Ownership – RSUs

Unlimited PTO + 14 paid holidays

Flexible hybrid work environment

401(k) with company match

Comprehensive Health & Wellness

Job summary

Seekr is building the next generation of enterprise AI infrastructure. As a Staff AI Infrastructure Engineer, you will design, build, and operate the platforms that enable large‑scale training, serving, evaluation, and deployment of foundation models and autonomous AI agents.

You will work across distributed systems, Kubernetes, GPU infrastructure, high‑performance inference, and enterprise AI platforms to deliver secure, scalable, and reliable systems spanning edge deployments to

Qualifications

• 8–12+ years of professional software engineering experience building distributed systems, cloud infrastructure, or large‑scale platform services.
• Architects systems, drives technical direction cross‑functionally.
• 4 year or higher degree or additional relevant experience, in addition to years of work experience.
• Demonstrated success designing and operating production Kubernetes environments supporting cloud‑native applications and distributed services.
• Strong software engineering skills using Python and one or more modern programming languages such as Go, Rust, or C++.
• Proven ability to design, build, and operate production AI or machine learning infrastructure.
• Expertise developing and optimizing large‑scale AI inference platforms, including GPU utilization, distributed inference, batching, caching, quantization, and accelerator performance.
• Familiarity with modern AI serving technologies such as vLLM, SGLang, TensorRT‑LLM, Triton Inference Server, Ray Serve, or similar platforms.
• Knowledge of distributed computing, networking, storage systems, cloud‑native architectures, and infrastructure automation using technologies such as Kubernetes, Helm, Argo CD, Docker, Prometheus, Grafana, OpenTelemetry, and Infrastructure‑as‑Code tools.
• Experience developing enterprise AI platforms, autonomous agents, or multi‑agent systems, including orchestration, tool execution, governance, observability, and evaluation.
• Familiarity with event‑driven architectures, distributed messaging systems, and public cloud platforms including AWS, Azure, Oracle Cloud Infrastructure, or Google Cloud Platform.
• Demonstrated technical leadership, including driving architectural decisions, mentoring engineers, and leading complex technical initiatives across cross‑functional teams.
• Demonstrated ability to analyze, profile, and optimize AI systems for performance, scalability, reliability, and cost across distributed compute environments.

Responsibilities

• Design, develop, deploy, and maintain production AI infrastructure supporting model training, fine‑tuning, inference, evaluation, and agentic AI workloads.
• Design and operate scalable Kubernetes‑based infrastructure supporting GPU‑accelerated workloads across cloud, on‑premises, hybrid, and edge environments.
• Architect and optimize high‑performance inference platforms capable of serving models ranging from resource‑constrained edge deployments to trillion‑parameter foundation models, with a focus on latency, throughput, scalability, reliability, and cost efficiency.
• Build and maintain distributed systems that enable reliable scheduling, orchestration, deployment, monitoring, and lifecycle management of AI workloads.
• Develop enterprise platforms supporting autonomous and multi‑agent AI systems, including secure tool execution, orchestration, memory, evaluation, governance, and observability.
• Design, implement, and automate AI infrastructure using Infrastructure-as-Code, GitOps, CI/CD pipelines, and modern software engineering practices.
• Evaluate and integrate emerging AI infrastructure technologies, model serving frameworks, hardware accelerators, and cloud‑native platforms to improve platform performance, scalability, and reliability.
• Collaborate with engineering, research, product, and cross‑functional teams to deliver secure, scalable, and production‑ready AI platforms.
• Lead technical design discussions, perform architecture reviews, mentor engineers, and establish engineering standards and best practices across the AI Infrastructure organization.
• Participate in production support activities, including troubleshooting complex distributed systems, performance tuning, incident response, and continuous operational improvement.

Skills

Distributed systems

Kubernetes

Python

Go/Rust/C++

Cloud infrastructure

AI platform engineering

Leadership

Performance optimization

Public cloud (AWS/Azure/GCP)

Infrastructure-as-Code

Education

4 year degree or higher

Tools

Terraform

Argo CD

Docker

Prometheus

Grafana

Job description

Seekr is building the next generation of enterprise AI infrastructure. As a Staff AI Infrastructure Engineer, you will design, build, and operate the platforms that enable large‑scale training, serving, evaluation, and deployment of foundation models and autonomous AI agents.

You will work across distributed systems, Kubernetes, GPU infrastructure, high‑performance inference, and enterprise AI platforms to deliver secure, scalable, and reliable systems spanning edge deployments to