{"id":2008537,"url":"https://alion.io/job/visian-data-scientist-gcp","title":"Data Scientist - GCP","company":{"id":3908419,"name":"Visian","domain":"visian.tech","url":"https://alion.io/company/visian","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Welcome to the Jungle","truth_index":null},"role":"Data Science","role_family":"Data Science","seniority":null,"employment_type":"freelance","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Lille, France"],"countries":["FR"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":41000,"max_usd":70000,"period":"year","method":"role_country_seniority_unknown","sample_n":174},"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"BigQuery","optional":false},{"name":"CI/CD","optional":false},{"name":"dbt","optional":false},{"name":"GCP","optional":false},{"name":"GitHub","optional":false},{"name":"Google BigQuery","optional":false},{"name":"LightGBM","optional":false},{"name":"Mypy","optional":false},{"name":"Optuna","optional":false},{"name":"Pytest","optional":false},{"name":"Python","optional":false},{"name":"SonarQube","optional":false},{"name":"SQL","optional":false},{"name":"Teradata","optional":false}],"status":"live","first_seen_at":"2026-09-23T09:36:35Z","employer_posted_date":null,"last_verified_at":"2026-09-23T09:36:35Z","board_verified":false,"closed_at":null,"days_open":26,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":26},"description":"Contexte :Équipe AI for PDP (Product Data Platform) produit des outils pour le pricing, l’optimisation de l’assortiment des produits.\nUne grande entreprise de distribution pilote ses prix sur des dizaines de milliers de références, par pays. L'enjeu : fournir aux équipes pricing un coefficient d'élasticité-prix par produit, exploitable pour l'ajustement quotidien, la promotion et la hausse stratégique.\n\nMissions :Data Collection et Preprocessing (dbt) : reconstruction de la vue produit hebdomadaire au niveau Business Unit à partir des transactions caisse et de l'historique de prix multi-magasins. Agrégation par prix médian (robuste aux prix extrêmes d'un magasin), filtre sur les produits, construction de baselines de demandes saisonnières, de tendances de demandes, de variations cumulées de prix (pour intégrer l’impact des changements de prix passés). Migration terraform + dbt + DataHub, source Teradata.\n\nModélisation : le modèle ne mesure pas l'élasticité, il prédit la demande hebdomadaire (LightGBM, Tweedie loss) à partir du prix, puis l'élasticité est dérivée en simulant 10 scénarios de variation de prix (-25% à +25%).\n\nPassage à l'échelle & performance : industrialisation sur 5 Business Units (France, Espagne, Portugal, Italie, Pologne), jusqu'à ~18M lignes et ~58k produits par Business Unit. Optimisation RAM : prune colonnes SQL-side, downcast des types, batchs de CV en générateur, chaînes en catégoriel.\n\nContrôle qualité : quality gates bloquant la publication par BU (comptage nombre de produits uniques, MAPE, WAPE, turnover-weighted WAPE), performance drift check sur un test set fait du dernier mois, typage des alertes (échec infra vs échec qualité données). Métriques calculées à la granularité de consommation (hebdo pour le tuning, mensuelle pour le gate).\n\nOrchestration ZenML : portabilité local et remote via stacks, exécution Vertex conteneurisée. Système de configurations à 3 couches (commun / env / BU), date d'exécution résolue une seule fois (backfills reproductibles). Packaging uv, CI qualité (ruff, mypy, pytest, sonarqube), step de tuning Optuna (TPE) optionnel.\n\nDocumentation fonctionnelle : ouverture de la boîte noire pour le métier : d'où viennent les données, comment la demande est transformée, ce que le coefficient signifie vraiment, et où il peut induire en erreur (ne pas moyenniser à plat des scénarios à l’interprétation différente, absence de stock, cannibalisation, améliorations potentielles de la solution). Objectif : un utilisateur métier peut se servir du coefficient avec le bon niveau de confiance.\n\nProfil recherché\nOutils et Environnement : \nPython \n\nZenML \n\nCI/CD \n\nGCP \n\nBigQuery \n\nGitHub \n\ndbt\n\nSQL\n\nVertex AI\n\nGithub Copilot\n\nTerraform\n\nGithub Actions\n\nDatadog\n\nCollibra","description_format":"text","description_chars":2749,"description_truncated":false,"requirements":{"experience_years_min":null,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":[],"lifecycle":[{"event":"open","at":"2026-10-07T12:33:56Z"}],"visa":[],"liveness":{"score":39,"band":"fade","label":"Fading","p_open":0.85,"p_active":0.619,"p_room":0.75,"age_days":26,"expected_fill_days":30,"reasons":["seen:26","velocity","win:late","comp:brand"],"computed_at":"2026-10-20T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/visian-data-scientist-gcp","json_url":"https://alion.io/job/visian-data-scientist-gcp.json","meta":{"generated_at":"2026-10-20T08:34:46Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":9343,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-21T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":3908419},"rest":"https://alion.io/mcp/rest/get_company?id=3908419"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fvisian-data-scientist-gcp"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fvisian-data-scientist-gcp"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fvisian-data-scientist-gcp"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/visian-data-scientist-gcp\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fvisian-data-scientist-gcp"}]}