We are seeking a highly skilled engineer to join our team focused on building and operating Large Language Model (LLM) services in a secure hybrid on‑premise and cloud environment. The role involves close collaboration with data scientists and backend developers to deliver reliable, scalable machine learning solutions.
Key responsibilities
Design, build, and maintain production‑grade ML systems centered on LLMs across hybrid on‑prem/cloud infrastructure.
Deploy, test, monitor, and manage ML models in containerised environments.
Develop and evolve the LLMOps lifecycle, including data preparation, fine‑tuning, evaluation, deployment, and monitoring.
Create CI/CD pipelines, orchestration solutions, and data versioning tools for ML workflows.
Implement automated anomaly detection, performance tracking, and cost‑optimisation for ML pipelines.
Required qualifications
Strong expertise in managing on‑premise and/or cloud LLM/MLOps infrastructure.
Proficiency with containerisation and orchestration platforms such as Kubernetes, Docker, Podman, EKS, PKS.
Hands‑on experience with MLflow, TensorFlow (TFX), Airflow, and major cloud providers (AWS or EU cloud).
Solid programming skills in Python, Unix/Bash, and infrastructure‑as‑code tools like Terraform or CloudFormation.
Familiarity with messaging systems (Kafka, Redis, RabbitMQ) and NoSQL databases (OpenSearch, MongoDB).
Nice to have
Knowledge of encryption mechanisms and ML security best practices.
Show the full description
Experience with the European Commission grant management ecosystem (eGrants).
