Senior LLMOps, RAG & infrastructure

Adlin Science, a company dedicated to the governance, quality management, and exploitation of multimodal biomedical data. As a Senior LLMOps, you will be responsible for building the platform's LLM/IA foundation, working closely with various teams, and prioritizing installable, auditable, and maintainable solutions.

You should have hands-on experience with LLMs or NLP/ML systems, excellent command of Python and PyTorch, and strong skills in Docker, Linux, CI/CD, and observability.

Responsibilities

• Your main responsibilities will include selecting and qualifying open models, defining a modular architecture, implementing local RAG, deploying and operating local inference engines, optimizing performance, and building pipelines for model management.
• Définir une architecture modulaire permettant de changer le modèle, le moteur d'inférence ou la stratégie RAG sans couplage excessif.
• Mettre en œuvre le RAG local : embeddings, recherche lexicale et vectorielle, recherche hybride, reranking.

Requirements

• Hands-on experience deploying and operating LLMs or NLP/ML systems under strong performance constraints.
• Excellent command of Python, PyTorch, the Transformers ecosystem and the architectural principles of language models.
• Mastery of at least one high-performance inference engine and experience with quantization and GPU sizing.
• Practical experience with RAG architectures, embeddings, hybrid search, reranking and evaluation of generative systems.
• Strong Docker, Linux, CI/CD, observability and artifact management skills in controlled environments.
• Security culture: secrets, access control, encryption, isolation, software supply chain and sensitive data processing.
• Ability to document, explain trade-offs and work with multiple teams without creating isolated technical debt.
• Autonomy and decision-making: you know how to scope your work and move forward even when things are not fully defined.
• Proactive mindset and critical thinking.
• Comfortable in dynamic, evolving environments: you thrive when processes are still being shaped.
• Open and constructive communication: you can break down technical concepts for non-technical audiences, share knowledge freely and foster collaborative dialogue.
• Master’s degree or PhD in computer science, AI, machine learning or a related field, or equivalent experience.
• Significant experience in ML Engineering, MLOps or AI infrastructure, with at least one LLM deployment actually operated in production.
• Hands-on profile, able to prototype, code, benchmark, diagnose and industrialize
• Rigor, autonomy, team spirit and ability to work in a context where traceability and quality come first.
• Fluent technical English.

Preferred

• Kubernetes, Terraform, MLflow, Prometheus/Grafana, OpenSearch and locally deployable vector databases such as Qdrant, Milvus or pgvector.
• PEFT/LoRA/QLoRA fine-tuning, distillation, distributed training and preparation of supervised datasets.
• Knowledge of healthcare sector constraints, GDPR, sensitive data and regulated environments.
• Experience with air-gapped, on-premise, appliance or edge environments, including controlled import procedures.
• Open-source contribution or experience reading and critically evaluating scientific papers.

Sélectionner, tester et qualifier des modèles ouverts compatibles avec le déploiement local et les contraintes de confidentialité.