Lead AI Platform Engineer - Scalable AI Infra & MLOps

Deutsche Telekom AG; La Coruña; Hybrid; EUR 90,000 - 120,000; Full time

Benefits offered by this job

Hybrid work model (remote/on-site)

Coursera training access

Language classes

Health insurance

Wellbeing & time off

Job summary

T-Systems Iberia is seeking a Lead AI Platform Engineer to design, build, and operate a scalable platform for autonomous AI agents. You will enable model serving, tool-calling, and state management with high-performance inference on GPU/TPU clusters, and implement autoscaling with Kubernetes/Knative.

You will also lead CI/CD pipelines, security controls, and developer tooling. The role blends software engineering, distributed systems, and AI infrastructure with a strong focus on reliability,

Qualifications

• 7+ years of software engineering experience.
• 4+ years building large-scale distributed systems.
• Proficient in Go or Rust, proficient in Python.
• Strong Kubernetes and Docker experience.

Responsibilities

• Design and own the core platform that builds, deploys, and runs autonomous AI agents.
• Build high-throughput, low-latency inference services on GPU/TPU clusters with autoscaling.
• Create CI/CD & MLOps pipelines for model versioning and releases.
• Define SLO/SLI, setup monitoring, and lead incident response.
• Implement security controls (IAM, sandboxed execution, data-residency policies).
• Deliver SDKs, CLI tools, and documentation for internal teams and partners.
• Mentor junior engineers and promote best-practice code standards.

Skills

Go

Rust

Python

Kubernetes

Docker

Helm

Triton

vLLM

TensorFlow Serving

Kafka

Pulsar

Prometheus

OpenTelemetry

Terraform

Pulumi

Vault

Education

PhD in Computer Science

MS in Computer Science

Tools

Terraform

Pulumi

Kafka

Pulsar

Prometheus

Grafana

OpenTelemetry

Vault

LangChain

Job description

T-Systems Iberia is seeking a Lead AI Platform Engineer to design, build, and operate a scalable platform for autonomous AI agents. You will enable model serving, tool-calling, and state management with high-performance inference on GPU/TPU clusters, and implement autoscaling with Kubernetes/Knative.

You will also lead CI/CD pipelines, security controls, and developer tooling. The role blends software engineering, distributed systems, and AI infrastructure with a strong focus on reliability,