DevOps Engineer - AI Runtime Services
DemandbaseAccount-Based Marketing company
Hyderabad, IndiaSenior
Scale Venture Partners
Sageview Capital
Sigma Partners
Adobe Systems
Altos Ventures
Costanoa Venture Capital
Software Engineering
About the role
TL;DR
DevOps Engineer for AI Runtime Services at Demandbase.
- •AI Runtime Services owns the shared runtime that AI at Demandbase runs on.
- •The team builds and supports internal AI solutions and the tooling and services the company uses to work with LLMs day to day.
- •Key Responsibilities Own the LLM gateway, reliability, cost control, observability, evals and experimentation infra, and caching and guardrails.
- •Ensure reliability, SLOs, on-call, incident response, and postmortems for the runtime.
- •Manage LLM spend, budgets, quotas, and make it legible and smaller.
- •Instrument systems, chase cardinality and cost in a metrics/logging backend, and build alerts that fire when they should.
- •Have hands-on familiarity with how LLM systems actually work and have built something with these tools.
- •Requirements Strong production infrastructure background: Kubernetes, AWS, Terraform, GitOps.
- •Python proficiency at a level where you're comfortable owning services and tooling in it.
- •Real on-call and incident-response experience.
- •Observability fluency beyond 'we have dashboards'.
- •Hands-on familiarity with how LLM systems actually work.
Required skills
KubernetesAWSPythonCI/CDLLMs
Nice-to-have skills
Terraform
Domain expertise
ai
Benefits & perks
Group Medical, Personal Accident, Term Life Insurance, Preventive healthcare, Mental health support, Fitness benefit, Car lease policy, Gratuity
Tech stack
AWSGoogle CloudTerraformKubernetesEKSPythonDatadogPrometheusGitLab CI
