Cloud Platform Engineer with a focus on Azure and AI automation

Who we are

We’re building an internal, AI‑powered developer platform designed to help engineering teams deliver software faster, more safely, and with greater confidence. The platform offers reusable workflow templates, AI‑assisted automation, CLI tooling, documentation, and evaluation pipelines-everything teams need to adopt AI‑enhanced engineering practices in a secure and scalable way.

You will not be a dedicated security engineer, but you will be expected to think carefully about how workflows can be abused, how agents can misbehave, how secrets can leak, and how permissions should be constrained. You should care about what happens when automation fails, when an AI agent produces unsafe output, or when a workflow is used in an unexpected way.
We are looking for an AI-native platform engineer who can build the tools and workflows that help engineering teams adopt AI safely and effectively.
You should enjoy building reusable systems, improving developer experience, automating repetitive work, and turning fast-moving AI capabilities into practical engineering infrastructure.

We’re looking for someone already fluent with modern AI‑native development tools. You should be comfortable using tools like GitHub Copilot, Cursor, Windsurf, Kiro, or similar to prototype, build, review, and iterate quickly.

What you'll be doing

• Build AI-Powered Developer Workflows


• You will design and implement reusable automation patterns that help engineering teams use AI safely and productively:


• Designing multi-step AI-assisted workflows for engineering tasks


• Creating reusable templates that work across different teams and technology stacks


• Writing prompts, workflow definitions, validation logic, and integration code


• Building tooling that helps teams adopt AI workflows without needing deep AI expertise


• Staying current with the rapidly evolving AI tooling and agentic development landscape


• Develop Internal Platform Capabilities


• You will help build and evolve the internal platform that teams use to discover, configure, validate, and run AI-powered automation:


• Building CLI tools and onboarding experiences


• Creating golden-path templates and self-service workflows


• Maintaining the pipeline that turns templates into production-ready artifacts


• Improving documentation, examples, and developer-facing guidance


• Reducing friction for teams adopting the platform


• Own AI Evaluation and Quality Gates


• You will help ensure that AI-powered workflows behave reliably, safely, and consistently before they are used in production contexts:


• Building and maintaining prompt evaluation pipelines


• Creating evaluation datasets for common, edge-case, and adversarial scenarios


• Developing custom evaluators, including code-based checks and LLM-as-a-judge patterns


• Defining quality thresholds for coherence, task adherence, safety, and reliability


• Designing CI checks that prevent regressions in AI-assisted workflows


• Support Secure and Scalable Platform Operations


• You will own the security and reliability foundations of the platform components you build:


• Managing cloud infrastructure needed for AI evaluation and workflow execution


• Working with Azure AI Foundry, model deployments, and identity federation patterns


• Designing secure CI/CD practices using least privilege and secrets management


• Implementing authentication and authorization patterns across the platform


• Considering prompt injection, data leakage, supply chain risks, and agent misbehavior


• Drive Adoption Across Engineering Teams


• You will work directly with engineering teams to make the platform useful, understandable, and easy to adopt:


• Partnering with teams during rollout


• Gathering feedback and turning it into platform improvements


• Writing clear documentation and onboarding guides


• Creating examples, templates, and reference implementations

What you'll bring along

• BSc/MSc in Computer Science or related field


• Minimum 3-5+ years as a Platform Engineer


• Infrastructure-as-code tools such as Terraform, Bicep, Pulumi, or CDK


• Proficient with AI‑assisted development tools - You regularly use AI coding tools or agentic workflows to accelerate software delivery


• Strong prompt‑crafting and AI evaluation skills - You can design effective prompts, critically assess AI‑generated code, and understand when AI tools are dependable versus when human oversight is required


• CI/CD and automation expertise - You have hands‑on experience building and maintaining automated pipelines


• Deep knowledge of GitHub Actions or similar systems - You are comfortable with reusable workflows, composite actions, pipeline‑as‑code patterns, and automated validation


• Python engineering capability - You can build evaluation scripts, custom validators, SDK integrations, automation utilities, and platform tooling


• Practical prompt engineering experience - You’ve designed, tested, and iterated on prompts within real engineering workflows


• Identity and security fundamentals — You understand OIDC, workload identity federation, secrets management, least‑privilege access, and secure automation patterns


• Configuration‑as‑code proficiency — You work comfortably with YAML, Markdown, declarative configuration, and docs‑as‑code practices


• You will be successful in this role if you can combine: the product mindset of a platform engineer, the practical instincts of a developer tools builder, the security awareness of a modern automation engineer, and the fluency of someone who actively uses AI to accelerate engineering work.


• Experience with any of the following would be valuable:


• AI evaluation frameworks such as Azure AI Evaluation SDK, promptfoo, RAGAS, DeepEval, or similar


• Agentic AI frameworks such as LangChain, CrewAI, AutoGen, OpenAI Assistants API, or similar


• Internal developer platforms, developer tooling, or Developer Experience engineering


• Software supply chain security concepts such as dependency scanning, action pinning, and SBOMs


• Statistical methods for evaluating non-deterministic systems


• AI safety and adversarial testing, including prompt injection and OWASP Top 10 for LLM applications


• Static site generators and docs-as-code pipelines


• Open-source contributions to developer tooling or automation projects