About the role At TechBiz Global, we are providing recruitment service to our TOP clients from our portfolio. We are currently seeking a Platform Engineer to join one of our clients' teams. If you're looking for an exciting opportunity to grow in an innovative environment, this could be the perfect fit for you. As a Platform Engineer, you will play a key role in the infrastructure team, helping to own, operate, and evolve the confidential compute platform that powers a secure, developer-facing AI API. The role is ideal for a hands‑on, infrastructure‑focused and security‑minded engineer who enjoys working across Kubernetes, cloud infrastructure, on‑premise systems, observability, automation, and low‑level platform hardening. Responsibilities Kubernetes Ownership: Maintain cluster operations end‑to‑end (upgrades, capacity, networking, RBAC, Helm charts, operations, and governance). Cloud Infrastructure: Run and evolve AWS, GCP, Azure, and other cloud environments using confidential compute primitives (Nitro Enclaves, Confidential VMs, Confidential Space) to scale the API and host adjacent workloads. On‑Premise Operations: Operate and extend our on‑premise confidential compute footprint (bare‑metal provisioning, network topology, hardware lifecycle). Observability: Design and operate metrics, logs, and traces pipelines for both cloud and on‑premise workloads, ensuring visibility where standard cloud‑native observability falls short. Infrastructure as Code: Provision and configure infrastructure via Ansible and IaC tools (Terraform or equivalent) with reproducible, code‑reviewed artifacts. Platform Hardening: Harden the platform through OS hardening, network segmentation, secret rotation, and reproducible images. Backend contribute to enclave‑side code (Rust preferred). Attestation strong systems programming background (C, C++, Go) with willingness to learn Rust. Experience with confidential computing internals (Intel TDX, AMD SEV‑SNP, AWS Nitro Enclaves). Knowledge of applied cryptography. Experience operating LLM inference workloads (vLLM, TensorRT‑LLM, GPU scheduling). Familiarity with the OpenAI API surface and surrounding SDK ecosystem. Reproducible builds and signed releases (Sigstore/cosign) and supply chain security practices. Open‑source contributions to point to. #J-18808-Ljbffr
Platform Engineer
