AI SRE: Scale, Resilience & GPU Inference

Seekr; Austin (TX); Hybrid; USD 140,000 - 200,000; Full time

Benefits offered by this job

Equity Ownership – RSUs

Unlimited PTO

14 paid company holidays

Hybrid work environment

401(k) with Company Match

Comprehensive Health & Wellness

Parental Leave

Job summary

Seekr is seeking an AI Site Reliability Engineer to ensure reliability, scalability, and safe operation of AI-powered services and infrastructure. You will blend software engineering with AI/ML operational expertise to deploy, monitor, and operate models, APIs, data pipelines, and platform services in production.

You will partner with AI/ML, Platform, Security, and Product teams to build dependable, performant, resilient systems ready to scale, with a focus on SLIs/SLOs, automation, and

Qualifications

• Bachelor's degree or equivalent practical experience in CS/engineering.
• 4+ years in Site Reliability Engineering, DevOps, or similar roles.
• Strong knowledge of distributed systems, cloud infra, networks, containers, and Kubernetes.
• Experience building and operating CI/CD pipelines and progressive deployment strategies.
• Proficiency with infrastructure-as-code and tools like Terraform.
• Experience with monitoring, logging, tracing, alerting, and incident management (Prometheus, Grafana, OpenTelemetry).
• Strong scripting and software development in Python or Go.
• Knowledge of SLIs/SLOs, capacity planning, and production-readiness reviews.

Responsibilities

• Build safe release processes with CI/CD automation, progressive deployments, validation, rollback, and health metrics.
• Define and operate SLIs/SLOs for AI APIs and critical services.
• Develop observability through metrics, logs, traces, dashboards, and SLO alerts.
• Lead on-call rotation, incident response, and blameless postmortems.
• Reduce toil with infrastructure as code, automation, and DR planning.
• Design automated load, stress, and scalability tests for AI production traffic.
• Set performance baselines, release thresholds, and capacity forecasts.
• Validate autoscaling, rate limiting, backpressure, graceful degradation, and recovery.
• Scale GPU-backed model inference on Kubernetes with batching and load balancing.
• Optimize inference engines and infra across GPUs, compute, networking, storage, and cost.
• Support reliable training workloads including distributed training and checkpointing.
• Collaborate with AI/ML, Platform, Security, and Product teams for production readiness.

Skills

Distributed systems

Cloud infrastructure

Kubernetes

CI/CD pipelines

Terraform

Monitoring & tracing

Prometheus

Grafana

OpenTelemetry

Python

Go

SRE / DevOps

Blameless postmortems

Education

Bachelor's degree in computer science, engineering, or a related field, or equivalent practical experience

Tools

Terraform

Prometheus

Grafana

OpenTelemetry

Kubernetes

NVIDIA Triton

PyTorch

DeepSpeed

FSDP

vLLM

Job description

Seekr is seeking an AI Site Reliability Engineer to ensure reliability, scalability, and safe operation of AI-powered services and infrastructure. You will blend software engineering with AI/ML operational expertise to deploy, monitor, and operate models, APIs, data pipelines, and platform services in production.

You will partner with AI/ML, Platform, Security, and Product teams to build dependable, performant, resilient systems ready to scale, with a focus on SLIs/SLOs, automation, and