Senior MLOps Engineer - Barcelona Onsite ML Platform

Impress; Barcelona; On-site; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Competitive salary

Dental benefits

Fresh fruits and snacks

Growth opportunities

Start-up vibe

Job summary

Impress is seeking a Lead MLOps Engineer to own the ML platform and infrastructure from development to production in Barcelona. You’ll design and maintain ML serving across AWS and GCP, manage multi-environment deployments with Terraform/Terragrunt, and run ML workloads on Kubernetes with robust observability.

The role requires 6+ years in ML engineering/MLOps, strong Docker and GPU optimization skills, and a track record delivering end-to-end ML services.

Qualifications

• 6+ years in ML engineering or MLOps with production responsibility.
• Strong cloud infra experience: AWS or GCP.
• Proficient in Terraform/Terragrunt for multi-env deployments.
• Experience deploying ML inference services in production (Triton, TorchServe).
• Docker expertise and GPU/ML compute optimization.
• Track record delivering end-to-end ML services to prod.
• Experience with event-driven architectures (SNS/SQS).
• Ability to lead and grow a small engineering team.

Responsibilities

• Own the ML platform, design and maintain serving infra across AWS/GCP.
• Manage multi-environment cloud infra with Terraform/Terragrunt.
• Run ML on Kubernetes: deployments, health checks, secrets, observability.
• Optimize GPU inference: profiling, batching, model conversion (ONNX/TorchScript).
• Drive cost efficiency: right-size compute, cost-per-inference metrics.
• Lead the team: define ownership areas and platform direction.
• Bridge ML and product: collaborate with researchers, PMs and clinical teams.

Skills

ML engineering

MLOps

Cloud infrastructure

Team leadership

Production ML

GPU compute optimization

End-to-end ML services

Tools

Terraform

Terragrunt

Docker

Kubernetes

Triton Server

TorchServe

FastAPI

ONNX/TorchScript

Job description

Impress is seeking a Lead MLOps Engineer to own the ML platform and infrastructure from development to production in Barcelona. You’ll design and maintain ML serving across AWS and GCP, manage multi-environment deployments with Terraform/Terragrunt, and run ML workloads on Kubernetes with robust observability.

The role requires 6+ years in ML engineering/MLOps, strong Docker and GPU optimization skills, and a track record delivering end-to-end ML services.