Senior MLOps Engineer - Edge AI & Inference

Hudl; Barcelona; Híbrido; EUR 104.000 - 147.000; Jornada completa

Descripción de la vacante

Hudl is hiring a Senior MLOps Engineer for its Hardware Group in Barcelona/London with remote options in the UK and Spain. You will build and scale the ML infrastructure powering Focus, our line of smart cameras.

You’ll own edge deployment pipelines, manage TensorRT optimization for embedded devices, and drive automation, reliability, and scalable update mechanisms across thousands of devices. Collaborate with Data Scientists, Embedded Engineers, and Product Managers to deliver robust solutions.

Formación

• Production MLOps experience deploying models to production with CI/CD, Docker, and Linux.
• Hands-on edge inference and model compilation for embedded hardware (TensorRT preferred).
• Strong collaboration with researchers and embedded engineers to translate constraints into solutions.
• Systems thinking for deploying to thousands of devices with canary releases and safe rollbacks.
• Bias toward action with initiative to fill gaps and help the team win.

Responsabilidades

• Build scalable Edge infrastructure to deploy models to fleets of devices.
• Own the model compilation platform to produce optimized inference engines and manage TensorRT, FP16/INT8, calibration, and validation.
• Collaborate with Data Scientists, Embedded Engineers, and Product Managers for smooth integration of features.
• Drive automation, telemetry, and monitoring of model drift, thermal impact, and latency in the field.
• Design architectures that handle edge failure gracefully and support updates in low-bandwidth environments.
• Mentor teammates on Python tooling, IaC, and CI/CD to raise automation and reliability.

Conocimientos

Production MLOps

Edge inference

CI/CD

Docker

Linux

TensorRT

Herramientas

TensorRT

Docker

Linux

Descripción del empleo

Hudl is hiring a Senior MLOps Engineer for its Hardware Group in Barcelona/London with remote options in the UK and Spain. You will build and scale the ML infrastructure powering Focus, our line of smart cameras.

You’ll own edge deployment pipelines, manage TensorRT optimization for embedded devices, and drive automation, reliability, and scalable update mechanisms across thousands of devices. Collaborate with Data Scientists, Embedded Engineers, and Product Managers to deliver robust solutions.