AI Platform Engineer

ClearRoute is an engineering consultancy bridging Quality Engineering, Cloud Platforms and Developer Experience. We help enterprises reliably bring high-impact digital products to market faster, cheaper, and safer, working with technology leaders facing complex business challenges.

We take as much pride in our people, culture and work-life balance as we do in making better software. We're not just making better software. We're making the making of software better. Collaborative, entrepreneurial and dedicated to problem solving, we bring the step change our customer need to sustain innovation. Our values challenge us to do the best we can for ClearRoute, our customers and most importantly our team. This is an opportunity for you to build the organisation from the ground up, use your voice to drive change and help transform organisations and problem domains.

The Role

We are looking for a Platform Engineer to join client-facing delivery teams and help design, build, and operate modern developer platforms. You will work across a range of industries and tech stacks, so adaptability matters as much as expertise.

On any given engagement you might be building a goldenpath CI/CD pipeline, hardening a Kubernetes cluster, migrating secrets management to Vault, or running a platform engineering workshop with a client's engineering teams. You will be expected to lead technical workstreams, pair with client engineers, and leave behind well-documented, production-ready infrastructure.

Increasingly, our clients are asking us to help them build the foundations for AI, from model-serving infrastructure and MLOps pipelines to safely integrating LLM powered tooling into existing developer workflows. You don't need to be an ML engineer, but you should be curious about this space and comfortable building the platform layer that makes AI workloads production ready.

What You'll Do

Platform & Infrastructure

• Design and deliver internal developer platforms (IDPs) that improve developer experience and accelerate software delivery.
• Build and maintain infrastructure-as-code using Terraform, Pulumi, or CDK and enforce code review and testing standards.
• Manage and optimise Kubernetes clusters (EKS, GKE, AKS) including multi-tenancy, networking, RBAC, and cost controls.
• Own CI/CD pipelines end-to-end: from source control policies through build, test, security scanning, artefact management, and deployment.
• Implement secrets management and certificate lifecycle automation using HashiCorp Vault or equivalent.

Reliability & Security

• Embed SRE practices: SLOs, error budgets, runbooks, on-call design, and blameless post-mortems.
• Integrate security tooling (SAST, DAST, dependency scanning, policy-as-code) into delivery pipelines.
• Design and test disaster-recovery strategies; automate them where possible.
• Ensure compliance with client security standards and relevant regulatory frameworks.

AI & Emerging Technology

• Design and operate infrastructure for AI/ML workloads: GPU node pools, model-serving runtimes (Triton, vLLM, BentoML), and vector database deployments (pgvector, Weaviate, Qdrant).
• Build and maintain MLOps pipelines model training, versioning, evaluation, and promotion to production using platforms such as Kubeflow, MLflow, or cloud-native equivalents.
• Integrate LLM APIs and AI agent frameworks into existing developer platforms, including prompt management, observability, cost controls, and rate-limit guardrails.
• Advise clients on AI readiness: data infrastructure, governance, security controls (model access policies, output filtering), and the organisational changes that sit alongside the technical work.
• Stay current with the fast-moving AI tooling landscape and bring relevant ideas back to the team and to clients.

Client Engagement

• Lead technical discovery sessions and platform assessments with client engineering and architecture teams.
• Translate client requirements into clear technical plans and communicate trade-offs to both technical and non-technical stakeholders.
• Coach and upskill client platform and application engineers through pairing, workshops, and code review.
• Produce high-quality documentation, architecture decision records (ADRs), and runbooks that clients can own after the engagement.

What We're Looking For....

Essential

• Solid hands-on experience with at least one major cloud provider (AWS preferred; GCP or Azure accepted).
• Production experience with Kubernetes and familiarity with the surrounding ecosystem (Helm, ArgoCD / Flux, Karpenter, Cilium, etc.).
• Strong infrastructure-as-code skills, Terraform is the baseline; other tools are a bonus.
• Practical experience designing or operating CI/CD systems (GitHub Actions, GitLab CI, Tekton, or similar).
• Comfort working in Linux environments and writing automation in Python, Bash, or Go.
• The ability to explain complex technical concepts clearly to a mixed audience.
• A consulting mindset: you care about solving the client's actual problem, not just delivering a deliverable.

Ideal (not required)

• Hands-on experience with AI/ML infrastructure: GPU scheduling on Kubernetes, model-serving runtimes, or MLOps tooling (Kubeflow, MLflow, Ray, etc.).
• Familiarity with LLM APIs (OpenAI, Anthropic, Bedrock, Vertex AI) and patterns for building reliable, observable AI-powered applications.
• Experience with vector databases or semantic-search infrastructure.
• Experience with event-streaming platforms such as Apache Kafka.
• Familiarity with configuration management tools (Chef, Ansible, or similar).
• Knowledge of mainframe environments or hybrid-cloud patterns.
• Relevant certifications: CKA/CKAD, AWS Solutions Architect, HashiCorp Vault, etc.
• Prior consultancy or client-facing delivery experience.

At ClearRoute, we believe diverse perspectives lead to better outcomes, and inclusion creates the conditions for everyone to thrive. We are proud to have built a family friendly working environment and have many employees who have caring responsibilities alongside work. We welcome applications from people who require flexibility and will be happy to discuss needs on an individual basis.

We are committed to fostering a culture where all team members feel respected, supported, and empowered to do their best work. We celebrate individuality and our differences and understand that some differences may mean that you require changes made to the interview process. We are happy to cater to your needs to make the interview accessible, if this is something you require please let us know by emailing us at [email protected]

Department Engineering Locations Cape Town Remote status Hybrid Employment type Full-time