Senior ML Engineer, LLM

Since 1993, the company has expanded from listings into payments, shipping and seller financing. We ship small changes daily rather than big quarterly releases.

We are backfilling a position after an internal move. This hire will help build out our ML platform: feature store, training pipelines, model registry and deployment. You can work from home anywhere in Spain. We have no office requirement. We keep meetings to a minimum and work mostly async. You need a reliable internet connection and somewhere quiet to work.

Your responsibilities:

• Deploy models behind low-latency APIs with FastAPI, Triton, TorchServe or vLLM.
• Handle on-call for the ML services the team owns.
• Track experiments, artifacts and versions in MLflow or Weights & Biases.
• Cut inference cost with quantization, batching and caching.
• Orchestrate pipelines with Kubeflow, SageMaker Pipelines, Vertex AI or Airflow.
• Maintain feature pipelines and a feature store such as Feast or Tecton.

Minimum qualifications:

• Hands-on experience with PyTorch, TensorFlow or JAX.
• BS or MS in computer science, engineering or a related field.
• Strong Python and solid engineering habits (testing, packaging, code review)
• Understanding of core ML concepts: overfitting, evaluation metrics, bias in training data.
• Familiarity with Docker, Kubernetes and a cloud ML platform (SageMaker, Vertex AI, Azure ML)

What you get:

• Private health insurance.
• Life insurance.
• Flexible start and finish times.
• Remote work allowance.

Candidates must be eligible to work in Spain.

Start: Within 30 days.

Demo job created on 11jobs for testing and demonstrations. It is not an actual opening at Keyway Apps S.L..