Building efficient generative models for weather forecasting

il y a 5 jours


Paris, Île-de-France Inria Temps plein

Le descriptif de l'offre ci-dessous est en Anglais

Niveau de diplôme exigé : Bac + 5 ou équivalent

Fonction : Stagiaire de la recherche

Contexte et atouts du poste

This master's thesis will be supervised by Emmanuel De Bézenac (ARCHES team, Inria Paris).

Mission confiée

Recent advances in generative modeling have opened new possibilities for representing complex geophysical fields. In weather forecasting, modern diffusion, flow-matching, and flow-based models have demonstrated strong performance, but current approaches struggle with multiscale atmospheric structure and with the fine–to–coarse interactions typical of physical fields. Improving the spectral and dynamical fidelity of these generative models is an important step toward reliable data-driven forecasting systems.

The master thesis will investigate how to adapt and refine generative modeling frameworks—particularly diffusion and flow-matching methods—to atmospheric data. The focus is on understanding how different scales of motion are represented during the generation process, how multiscale structures propagate through the model dynamics, and how model design choices influence numerical stability and physical realism. The work will contribute to the development of next-generation AI weather models capable of representing both global-scale patterns and fine-scale variability.

Principales activités
  • Study existing generative modeling frameworks used in scientific data (diffusion, flow matching, deterministic flows) and analyse how they behave on multiscale atmospheric fields.
  • Explore strategies for representing scale interactions during the generation process, such as alternative noise designs, interpolation schemes, or multiscale parameterizations.
  • Develop and test model adaptations tailored to weather data—e.g., architecture choices, training procedures, or sampling methods that improve spectral accuracy and physical consistency.
  • Contribute to prototype implementations and small-scale experiments within the ARCHES weather modeling effort.
Compétences

Technical skills and level required :

  • Bachelors and Master's degrees in Computer Science (Informatique), statistics, mathematics, or a related field
  • Machine learning, data mining, statistics, and/or AI coursework and/or projects
  • Familiarity with modern machine learning / deep learning software, tools, pipelines

Languages :

  • Written competency in English
  • Oral competency in English or French
Avantages
  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training
  • Social security coverage
Informations générales
  • Thème/Domaine : Optimisation, apprentissage et méthodes statistiques

Statistiques (Big data) (BAP E)
- Ville : Paris
- Centre Inria : Centre Inria de Paris
- Date de prise de fonction souhaitée :
- Durée de contrat : 6 mois
- Date limite pour postuler :

Attention: Les candidatures doivent être déposées en ligne sur le site Inria. Le traitement des candidatures adressées par d'autres canaux n'est pas garanti.

Consignes pour postuler

Sécurité défense :

Ce poste est susceptible d'être affecté dans une zone à régime restrictif (ZRR), telle que définie dans le décret n° relatif à la protection du potentiel scientifique et technique de la nation (PPST). L'autorisation d'accès à une zone est délivrée par le chef d'établissement, après avis ministériel favorable, tel que défini dans l'arrêté du 03 juillet 2012, relatif à la PPST. Un avis ministériel défavorable pour un poste affecté dans une ZRR aurait pour conséquence l'annulation du recrutement.

Politique de recrutement :

Dans le cadre de sa politique diversité, tous les postes Inria sont accessibles aux personnes en situation de handicap.

Contacts
  • Équipe Inria : ARCHES
  • Recruteur :

De Bezenac Emmanuel /

L'essentiel pour réussir
  • Strong background in machine/deep learning and mathematics
  • Knowledge of computer vision and image processing
  • Familiarity with generative models (GANs, diffusion, consistency models) and deep learning architectures (CNNs, transformers)
  • Proficiency in Python and experience with deep learning frameworks (PyTorch and/or JAX)
  • Appetite for theoretical and applied scientific research
  • Ability to conduct exploratory research with significant autonomy
A propos d'Inria

Inria est l'institut national de recherche dédié aux sciences et technologies du numérique. Il emploie 2600 personnes. Ses 215 équipes-projets agiles, en général communes avec des partenaires académiques, impliquent plus de 3900 scientifiques pour relever les défis du numérique, souvent à l'interface d'autres disciplines. L'institut fait appel à de nombreux talents dans plus d'une quarantaine de métiers différents. 900 personnels d'appui à la recherche et à l'innovation contribuent à faire émerger et grandir des projets scientifiques ou entrepreneuriaux qui impactent le monde. Inria travaille avec de nombreuses entreprises et a accompagné la création de plus de 200 start-up. L'institut s'efforce ainsi de répondre aux enjeux de la transformation numérique de la science, de la société et de l'économie.


  • Generative AI Developer

    il y a 1 semaine


    Paris, Île-de-France Equativ Temps plein

    About The TeamAt Equativ, we're on a mission to develop advertising technologies that empower our customers to reach their digital business goals. The impact of Generative Artificial Intelligence on advertisers is projected to disrupt part of the industry and Equativ has been undergoing a significant transformation to embed this technology at the core of our...


  • Paris, Île-de-France Weathernews Inc. Temps plein

    Weathernews is one of the world's largest private meteorological services companies (publicly traded) with headquarters in Tokyo. It offers a comprehensive range of weather and climate services covering the entire world using its proprietary solutions and technologies, including its own weather satellites. These high value-added services cover many sectors...


  • Paris, Île-de-France Inria Temps plein

    Le descriptif de l'offre ci-dessous est en AnglaisType de contrat : CDDNiveau de diplôme exigé : Thèse ou équivalentFonction : Post-DoctorantContexte et atouts du posteThe position will be in the framework of the ERC Starting Grant DYNASTY (Dynamics-Aware Theory of Deep Learning).The position might include traveling to conferences for paper presentation....

  • Research Engineer

    il y a 6 jours


    Paris, Île-de-France Institute of Foundation Models Temps plein

    About the Institute of Foundation Models We are a dedicated research lab for building, understanding, using, and risk-managing foundation models. Our mandate is to advance research, nurture the next generation of AI builders, and drive transformative contributions to a knowledge-driven economy. As part of our team, you'll have the opportunity to work on...

  • Research Engineer

    il y a 6 jours


    Paris, Île-de-France Institute of Foundation Models Temps plein

    About the Institute of Foundation ModelsWe are a dedicated research lab for building, understanding, using, and risk-managing foundation models. Our mandate is to advance research, nurture the next generation of AI builders, and drive transformative contributions to a knowledge-driven economy. As part of our team, you'll have the opportunity to work on the...

  • Expert IA Générative/fa

    il y a 2 semaines


    Paris, Île-de-France Free-Work Temps plein

    Expert IA Générative - Sénior avec un minimum de 7 ans d'expériences sur des projets similaires ;Compétences requises :Python, frameworks d'IA (PyTorch, TensorFlow, Hugging Face), APIs d'IA générative (OpenAI, Anthropic, etc.), bases de données vectoriellesTransformers, diffusion models, GANs, etc.Techniques d'optimisation des modèles (quantization,...


  • Paris, Île-de-France JPMorgan Chase Temps plein

    The Legal Entity Loss Forecasting team provides solutions to legal entities, including capital and stress loss assessment to assist Internal Capital Assessment Adequacy Process (ICAAP), regulatory prescribed exercise, climate stress testing. The team recently expanded its scope to lead IFRS 9 production.As an Associate within our Legal Entity Loss...

  • Building Manager,

    il y a 2 semaines


    Paris, Île-de-France Beacon Martech Temps plein

    I'm conducting a confidential research study for a client on the future of building-technology infrastructure, and I'm looking for an experienced professional who can join a 60-minute one-to-one interview to share deep insights.Your expertise should be in one or more of the following areas: Autonomous or self-optimising buildings Smart buildings & IoT...


  • Paris, Île-de-France AXA Temps plein

    About AXAAs a world-leading insurance company, we act for human progress by protecting what matters. With 153,000 employees in 54 countries working for 105 million customers, we've created a truly dynamic and vibrant community. Inclusion and diversity link closely with our values, and together we're nurturing a culture of respect, for each other, for our...


  • Paris, Île-de-France Covea Temps plein

    STAGE - Voice_bots avec IA générative notre expérience client, nous développons des solutions conversationnelles pour accueillir le client 24/7, reconnaître son besoin et traiter sa demande. Nous souhaitons moderniser cette approche en intégrant des technologies d'IA générative et des architectures plus flexibles.   Mots clés : MCP, LLM, RAG,...