AEROCONTACT
Website:
aerocontact.com
Job details:
Safran est un groupe international de haute technologie opérant dans les domaines de l'aéronautique (propulsion, équipements et intérieurs), de l'espace et de la défense. Sa mission : contribuer durablement à un monde plus sûr, où le transport aérien devient toujours plus respectueux de l'environnement, plus confortable et plus accessible. Implanté sur tous les continents, le Groupe emploie 100 000 collaborateurs pour un chiffre d'affaires de 27,3 milliards d'euros en 2024, et occupe, seul ou en partenariat, des positions de premier plan mondial ou européen sur ses marchés. Safran est la 2ème entreprise du secteur aéronautique et défense du classement « World's Best Companies 2024 » du magazine TIME. Safran Electrical & Power est l'un des leaders mondiaux des systèmes électriques aéronautiques. La société est un acteur clé dans le domaine de l'électrification des équipements et de la propulsion électrique et hybride. Elle compte 14 000 collaborateurs répartis dans 13 pays.
Descriptif mission
We are seeking a experienced Generative AI engineer to lead the design and development of an AI platform that leverages Large Language Models (LLMs) and other cutting-edge AI technologies. In this role, your core responsibilities are Architect and build GenAI-powered applications using LLMs and advanced RAG pipelines for technical documentation, maintenance, and support workflows. Design and implement retrieval-augmented generation (RAG) systems leveraging vector databases and semantic search for contextual information retrieval. Integrate and fine-tune LLMs (OpenAI, Anthropic, Amazon Bedrock, HuggingFace, etc.) for domain-specific tasks and continuous improvement. Develop robust evaluation frameworks for LLM output (relevancy, faithfulness, summarization, contextual accuracy). Build and deploy microservices and APIs for GenAI solutions, ensuring high availability, scalability, and secure access. Collaborate with product, domain, and platform teams to refine requirements and deliver innovative GenAI solutions. Stay current with GenAI trends, frameworks, and best practices to future-proof solutions for evolving enterprise needs.
Required Technical Skills GenAI & LLMs: OpenAI, Anthropic, Amazon Bedrock, HuggingFace Transformers, LangChain, RAG architectures, prompt engineering, fine-tuning. Vector Databases & Semantic Search: Pinecone, FAISS, Milvus, Weaviate, Elasticsearch/OpenSearch with vector support. GenAI Evaluation & Monitoring: G-Eval, Prometheus, QAG scorer, MLflow, DataDog, CloudWatch, custom LLM-as-a-judge frameworks. API & Microservices: RESTful API design, GraphQL, FastAPI, Flask, OAuth2/JWT, containerization (Docker, Kubernetes). Security & Compliance: IAM, KMS, VPC endpoints, S3 Object Lock, CloudTrail, encryption policies, GDPR/industry compliance. DevOps for GenAI: CI/CD pipelines (GitHub Actions, CodePipeline), Terraform, AWS CDK, CloudFormation for automated deployment and scaling of GenAI services. Data Modeling for GenAI: Metadata tagging, schema design, data quality management for LLM training and inference. Multi-modal Retrieval: Experience with text, images, video, telemetry for comprehensive GenAI solutions. Preferred Experience Building enterprise-grade RAG systems for technical documentation, support, or maintenance workflows. Implementing multi-modal retrieval in large-scale environments. Familiarity with continuous evaluation and improvement of LLMs in production (A/B testing, feedback loops). Exposure to regulated industries (aviation, manufacturing, healthcare) with strict compliance and audit requirements. Working with multi-cloud architectures (AWS, Azure, GCP) and hybrid deployments. Advanced knowledge of MLOps: model deployment, monitoring, rollback, and lifecycle management.
Click on Apply to know more.