DevOps Engineer - AI Runtime Services
- Role
- DevOps
- Employment
- Full-time
Open to IN, PK only. Set where you work from to check your eligibility.
No BS summary
DevOps/SRE engineer in India for AI runtime infrastructure. Must have production Kubernetes, AWS, Terraform, GitOps, Python, on-call/incident response, observability, and hands-on LLM systems experience.
Core skills
Required skills
Optional skills
Introduction to Demandbase:
Demandbase is the only pipeline AI platform that empowers GTM teams to automate growth at scale. With a unified view of data, insights, actions, and outcomes, B2B enterprises can seamlessly align and execute their account-based GTM strategies with confidence. Thousands of businesses trust Demandbase to maximize revenue, minimize waste, and consolidate their data and tech stacks – all in one platform.
As a company, we’re as committed to growing careers as we are to building world-class technology. We invest heavily in people, our culture, and the community around us. We have also continuously been recognized as One of The Best Places To Work in the San Francisco Bay Area by Fortune, and One of The 60 Best Companies To Sell For by Selling Power. Our offices are located in San Francisco, New York, Austin, Seattle, India, and the United Kingdom.
About the Role
AI Runtime Services owns the shared runtime that AI at Demandbase runs on — two ways. First, it's the layer that enables and supports the AI features in the Demandbase platform: product teams ship LLM features on top of it without reinventing model access, spend control, safety, and observability. Second, the team builds and supports internal AI solutions — the tooling and services the company uses to work with LLMs day to day. The pillars underneath both: the LLM gateway, cost controls, observability, evals infra, caching, and guardrails.
The surface is broad and the team is early. You won't be handed a narrow slice: expect to move across the gateway one week and the ingest pipeline the next — and across product-facing runtime and internal tooling — and to own what you build in production.
What you'll own
- The LLM gateway. The single front door to every model provider we use — keys, routing, rate limits, failover, provider quotas. When it's down, every AI feature at Demandbase is down.
- Reliability, for real. SLOs, on-call, incident response, and the postmortems for the runtime. This is a genuine SRE ownership role, not "build it and let someone else run it."
- Cost control. Per-team and per-model attribution, budgets, quotas. LLM spend is the kind of line item that quietly triples; your job is to make it legible and then make it smaller.
- LLM observability. Traces, spans, prompt/response capture, ingest and billing visibility for every AI feature in the company.
- Evals and experimentation infra. The shared harnesses, datasets, and scoring plumbing product teams use to know whether a prompt or model change actually made things better.
- Caching and guardrails. Response and semantic caching to cut latency and redundant spend; input/output safety, PII handling, and policy enforcement at the gateway.
What we need
- Strong production infrastructure background: Kubernetes, AWS, Terraform, GitOps. You've operated systems that people were paged for, and you've been the one paged.
- Python, at a level where you're comfortable owning services and tooling in it — not just scripting.
- Real on-call and incident-response experience. You can talk about an incident you ran, what you got wrong, and what you changed afterward.
- Observability fluency beyond "we have dashboards": you've instrumented systems, chased cardinality and cost in a metrics/logging backend, and built alerts that fire when they should.
- Hands-on familiarity with how LLM systems actually work. You don't need production ML experience. But you need to have built something with these tools — an agent, a RAG pipeline, an internal tool — and to have used evals or experiments to decide whether it was any good. Tokens, context windows, prompt/response tracing, and why an eval suite is fundamental should all be familiar ground. Candidates who have only read about this are not a fit.
Nice to have
- An LLM gateway or proxy (LiteLLM or similar) in production.
- LLM observability tooling: Datadog LLM Observability, LangSmith, Braintrust, Arize, or similar.
- Eval frameworks and LLM-as-judge scoring in a real workflow, not a demo.
- FinOps instincts — cost attribution, showback, quota design.
- Guardrails, PII detection, or content-filtering systems.
- GCP alongside AWS.
Our stack
AWS - GCP · EKS, Flux/GitOps, Karpenter · Python · LiteLLM · Datadog (LLM observability, APM) · Prometheus, Loki, ClickHouse · Terraform · GitLab CI
Benefits
Our benefits include Group Medical, Personal Accident, and Term Life Insurance for comprehensive protection. Preventive healthcare covers dental, vision, and OPD needs, complemented by strong mental health support. We also provide a fitness benefit, car lease policy, and gratuity for long-term financial well-being.
Our Commitment to Diversity, Equity, and Inclusion at Demandbase
At Demandbase, we believe in creating a workplace culture that values and celebrates diversity in all its forms. We recognize that everyone brings unique experiences, perspectives, and identities to the table, and we are committed to building a community where everyone feels valued, respected, and supported. Discrimination of any kind is not tolerated, and we strive to ensure that every individual has an equal opportunity to succeed and grow, regardless of their gender identity, sexual orientation, disability, race, ethnicity, background, marital status, genetic information, education level, veteran status, national origin, or any other protected status. We do not automatically disqualify applicants with criminal records and will consider each applicant on a case-by-case basis.
We recognize that not all candidates will have every skill or qualification listed in this job description. If you feel you have the level of experience to be successful in the role, we encourage you to apply!
We acknowledge that true diversity and inclusion requires ongoing effort, and we are committed to doing the work required to make our workplace a safe and equitable space for all. Join us in building a community where we can learn from each other, celebrate our differences, and work together.
Unsolicited Submissions
At Demandbase, we value thoughtful partnerships and direct connections with candidates. We’re not accepting unsolicited resumes or outreach from third-party recruiting agencies. Any unsolicited submissions will not be reviewed, and no fees will be paid.
What you'll do
- Own the LLM gateway as the single front door to model providers, including keys, routing, rate limits, failover, and provider quotas.
- Own reliability for the AI runtime, including SLOs, on-call, incident response, and postmortems.
- Manage LLM cost control, including per-team and per-model attribution, budgets, and quotas.
- Build and maintain LLM observability, including traces, spans, prompt/response capture, ingest visibility, and billing visibility for every AI feature.
- Build evals and experimentation infrastructure, including shared harnesses, datasets, and scoring plumbing for product teams.
- Implement caching and guardrails, including response and semantic caching, input/output safety, PII handling, and policy enforcement at the gateway.
- Move across the LLM gateway, ingest pipeline, product-facing runtime, and internal tooling.
- Own what you build in production.
What they require
- Strong production infrastructure background with Kubernetes, AWS, Terraform, and GitOps.
- Experience operating systems that people were paged for and being the person paged.
- Python proficiency sufficient to own services and tooling, not just scripting.
- Real on-call and incident-response experience, including being able to discuss an incident you ran, what went wrong, and what changed afterward.
- Observability fluency beyond dashboards, including instrumenting systems, chasing cardinality and cost in a metrics/logging backend, and building alerts that fire when they should.
- Hands-on familiarity with how LLM systems work.
- Experience building something with LLM tools, such as an agent, a RAG pipeline, or an internal tool.
- Experience using evals or experiments to decide whether an LLM system was good.
- Familiarity with tokens, context windows, prompt/response tracing, and why an eval suite is fundamental.
- Candidates who have only read about LLM systems are not a fit.
- Preferred: An LLM gateway or proxy in production.
- Preferred: Eval frameworks and LLM-as-judge scoring in a real workflow, not a demo.
- Preferred: FinOps instincts, including cost attribution, showback, and quota design.
- Preferred: Guardrails, PII detection, or content-filtering systems.
- The company is not accepting unsolicited resumes or outreach from third-party recruiting agencies.
Benefits
- Group Medical Insurance.
- Personal Accident Insurance.
- Term Life Insurance.
- Preventive healthcare covering dental, vision, and OPD needs.
- Mental health support.
- Fitness benefit.
- Car lease policy.
- Gratuity for long-term financial well-being.
Demandbase is the only pipeline AI platform that empowers GTM teams to automate growth at scale. With a unified view of data, insights, actions, and outcomes, B2B enterprises can seamlessly align and execute their account-based GTM strategies with confidence.