Lead AI Platform Engineer — Scalable AI Infra & MLOps

T-Systems Iberia; España; Remote; EUR 90,000 - 140,000; Full time

Benefits offered by this job

Life and accident insurance

Social fund

Coursera training access

Job summary

T-Systems Iberia is seeking a LeadAI Platform Engineer to design, build, and operate a scalable, production-grade platform for deploying autonomous AI agents, including model serving, tool-calling, and state management.

You will develop high-performance, low-latency inference services on GPU/TPU clusters, implement autoscaling with Kubernetes/Knative, and build CI/CD and MLOps pipelines for model versioning and canary releases.

Qualifications

• Proficient in Go or Rust and Python; strong Kubernetes, Docker, Helm experience.
• Hands-on with model serving frameworks (Triton, vLLM, TensorFlow Serving) and GPU/TPU workloads.
• Experience with event streaming (Kafka/Pulsar) and infrastructure-as-code (Terraform/Pulumi).
• Solid knowledge of LLM concepts, retrieval-augmented generation, and tool-use APIs.
• Strong debugging, observability (Prometheus, Grafana, OpenTelemetry), and security (IAM, Vault) skills.
• Excellent communication and a bias toward shipping reliable, production-grade code.

Responsibilities

• Design and own the core platform that builds, deploys, and runs autonomous AI agents (model serving, tool-calling, state management).
• Build high-throughput, low-latency inference services on GPU/TPU clusters and implement autoscaling with Kubernetes/Knative.
• Create CI/CD & MLOps pipelines for model versioning, canary releases, and rollback.
• Define SLO/SLI, set up monitoring (Prometheus, OpenTelemetry), and lead incident response.
• Implement security controls (IAM, sandboxed execution, data-residency policies).
• Deliver developer-friendly SDKs, CLI tools, and documentation for internal teams and external partners.
• Mentor junior engineers and champion best-practice code standards.

Skills

Go

Rust

Python

Kubernetes

Docker

Helm

GPU/TPU workloads

Education

PhD or MSc in CS or related field

Tools

Kubernetes

Docker

Helm

Triton

vLLM

TensorFlow Serving

Kafka

Pulsar

Terraform

Pulumi

LangChain

AutoGPT

FAISS

Milvus

Prometheus

OpenTelemetry

Vault

Job description

T-Systems Iberia is seeking a LeadAI Platform Engineer to design, build, and operate a scalable, production-grade platform for deploying autonomous AI agents, including model serving, tool-calling, and state management.

You will develop high-performance, low-latency inference services on GPU/TPU clusters, implement autoscaling with Kubernetes/Knative, and build CI/CD and MLOps pipelines for model versioning and canary releases.