Senior Cloud Platform Engineer (Azure & AI Foundry Specialization)
Location: Oaks, PA
Type : Contract
Need candidate to work onsite from Day 1 (3 days a week – Hybrid basis) – NO REMOTE WORK
Experience: 10+ years overall, including 6+ years hands-on cloud infrastructure engineering
INDICATIVE RESPONSIBILITIES
The platform is being designed as the engagement progresses, so responsibilities will evolve. Indicative, and not limited to:
• Build and operate the cloud environments agents run in, across managed AI services, Kubernetes and other runtime targets, delivered as infrastructure-as-code with promotion from lower environments through to production.
• Design and implement the network posture for a hybrid estate: virtual networks and subnets, private endpoints and private DNS, cross-cloud connectivity, and private paths to on-premises infrastructure.
• Provision and operate the AI services the platform runs on, including Azure AI Foundry and Azure OpenAI: projects, capability hosts, agent image registry, role-based access control, model deployments, quota and throughput management.
• Build the supporting infrastructure AI workloads depend on: container registries and image supply chain, secrets and key management, managed identity for service-to-service calls, and the vector or search services agents retrieve from.
• Manage model capacity and cost: deployment sizing, throughput and rate-limit configuration, regional placement and failover, and the usage telemetry that makes consumption attributable.
• Configure and validate model access paths from every runtime to cloud-hosted models, other providers, and an on-premises GPU cluster, including latency and failover testing.
• Build the Kubernetes footprint supporting agents deployed outside managed services, including namespace design, workload identity and ingress.
• Establish network paths for third-party and self-hosted platform services, such as observability backends and model providers outside the primary cloud, covering private connectivity or controlled egress, DNS resolution, certificate handling and the firewall allowances each integration requires.
• Work with client security and infrastructure teams to take environment changes through review, including firewall, egress and data residency considerations.
• Act as the team’s reference point for Azure AI and Foundry capabilities, assessing what is production-ready, what is in preview, and what the platform should depend on.
• Produce the topology documentation, architecture decision records and runbooks that the wider team and the client operate from.
MUST HAVE
• 6+ years hands-on cloud infrastructure engineering in production environments, covering compute, networking, identity, storage and monitoring.
• 4+ years Microsoft Azure specifically, at production depth.
• Working experience with at least one hyperscaler beyond Azure (AWS or Google Cloud), including its networking and identity model. You will be expected to reason about cross-cloud connectivity, not only Azure-internal design.
• Demonstrable Azure AI Foundry experience: model deployments, quota and throughput management, and content filtering configuration.
• Current Azure certification: Azure Solutions Architect Expert (AZ-305) or Azure Administrator Associate (AZ-104).
• 4+ years infrastructure-as-code to production standard using Terraform or equivalent, including module design, state management and multi-environment promotion.
• 3+ years Kubernetes in production, including cluster networking, workload identity, ingress and namespace design.
• 3+ years enterprise cloud networking: virtual networks and VPCs, subnets, security groups, private endpoints, private DNS resolution and cross-network connectivity.
• 2+ years hybrid cloud and on-premises connectivity, using ExpressRoute, Direct Connect, site-to-site VPN or equivalent, including private DNS resolution across boundaries and firewall and egress rules. On-premises infrastructure is a first-class runtime target on this platform, not an edge case.
• 2+ years integrating third-party or self-hosted services into an enterprise network, including private connectivity or controlled egress, DNS resolution, TLS and certificate management, and working the firewall and security review needed to get each path approved.
• 3+ years building infrastructure for AI or data-intensive workloads, on any major cloud: model or inference endpoints, container registries and image supply chain, managed identity between services, secrets management, and the capacity and quota model these workloads run under.
• Working knowledge of the AI service landscape across hyperscalers, not one vendor only. Comparable services on AWS or Google Cloud, such as Bedrock or Vertex AI, and an understanding of what differs between them in networking, identity and cost.
• 2+ years building CI/CD pipelines for infrastructure delivery using GitHub Actions, Azure DevOps or equivalent.
• Working knowledge of LLM platform operations: model endpoints, token throughput, quotas and rate limits, streaming responses, and how inference cost accrues and is attributed.
PREFERRED
• Azure AI Foundry Agent Service experience, including hosted agents, capability hosts or agent registration.
• Experience operating self-hosted or GPU-based inference infrastructure, including capacity and throughput planning for on-premises model serving.
• Experience in financial services or another regulated industry, where security review governs the pace of environment change.
• Familiarity with OpenTelemetry or platform observability tooling, particularly for AI workload telemetry.
• Exposure to AI gateway or model-routing patterns, such as API gateway policies applied to model traffic, token-based rate limiting or content filtering.
• Familiarity with vector or semantic search services such as Azure AI Search, or a comparable managed retrieval service.
• Microsoft Azure AI Engineer Associate (AI-102), or an equivalent certification on another hyperscaler.
Tekshapers is an equal opportunity employer and will consider all applications without regards to race, sex, age, color, religion, national origin, veteran status, disability, sexual orientation, gender identity, genetic information or any characteristic protected by law
Never miss an opportunity! Create an alert based on the job you applied for.
