Stage Innovation Ingnieur Intelligence Articielle Gnrative
Stage Innovation Ingnieur Intelligence Articielle Gnrative
Employer Active
Job Alert
You will be updated with latest job alerts via email
Share
Job Alert
You will be updated with latest job alerts via email
Job Description
We are a leading Engineering and IT consultancy operating across 30 countries paving the way in various sectors including Aeronautics Space Defence Automotive Rail & Mobility Energy & Environment Life Sciences & Health and Telecoms.
Our mission is to enable and support our customers development strategies technological advancements and sustainability initiatives. We are united by a common purpose: building tomorrows world today.
Our Innovation Lab brings together industry challenges cuttingedge technologies and an enthusiastic team of innovation engineers. Our projects are strategically focused on delivering inventive solutions to address sectors & customers challenges drive digital transformation and enable businesses to thrive in the modern landscape.
Project: Graph RAG for Aerospace
Project GRACE (Graph RAG for Aerospace) aims to apply the newly emerging trend of Graph RAG to the field of Aerospace. It hopes to do so by applying the established techniques behind RAG to a bespoke knowledge graph of an Aero engine such that the Aero components represent nodes in the graph and the connections represent edges.
The aim of this project is to test and validate the hypothesis that this approach is more effective than traditional RAG when applied to Aerospace as it allows Engineers to ask more varied and complex Aerospace questions obtain more reliable responses and provide increased transparency to the users regarding the logic the LLM followed to provide its response.
Another key part of this project will be to apply Domain adaptive pretraining (with a custom tokenizer) and supervised finetuning for question answering to a local LLM on a large corpus of Aerospace data and potentially test the increased efficacy of applying Graph RAG with the resulting model.
A highlevel longterm goal is for this project to serve as a blueprint for how RAG and LLMs more generally could be applied within the Aerospace sector to many more aspects of their workflows.
Qualifications :
Working towards a Masters degree (last year) in:
- Artificial Intelligence Machine Learning Data Science Computer Science with a preference for practical skills in NLP LLM Transformers and/or Computer Vision.
- And/or full stack development (front end and back end).
- And/or Digital Twin / Digital Thread in an engineering environment.
- And/or Robotic.
Skills:
- A strong level of Python programming writing clean code and testing thoroughly is essential.
- A high level of proficiency in LLMs and RAG would be highly advantageous.
- Knowledge of Graph RAG would be advantageous but not essential.
- Experience in one or more LLM frameworks such as Langchain LlamaIndex or HuggingFace would be highly advantageous.
- Experience in Neo4j would also be advantageous. Knowledge of Aero engines would be nice to have but not essential.
- English level: C1 minimum
The ideal candidate is curious positive creative collaborative and looking to challenge themselves. We seek individuals who thrive in dynamic environments embracing change and ambiguity while demonstrating readiness to contribute to impactful projects within crossfunctional teams.
We also celebrate multiple approaches and points of view. We believe diversity drives innovation so we are building a culture where difference is valued and encouraged.
Remote Work :
No
Employment Type :
Intern
Employment Type
Intern
