{"id":2007266,"url":"https://alion.io/job/ouicoding-tech-lead-expert-data-retrieval-rag-hf","title":"Tech lead Expert Data Retrieval RAG H/F","company":{"id":2940665,"name":"OUIcoding","domain":"ouicoding.com","url":"https://alion.io/company/ouicoding","size_band":null,"is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"lead","employment_type":"freelance","work_mode":"hybrid","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Courbevoie, France"],"countries":["FR"],"hiring_countries":[],"hiring_countries_total":0,"salary":{"min":400,"max":600,"currency":"EUR","period":"day","gross":null,"usd_annual":168750},"salary_estimate":null,"experience_years_min":null,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Apache Kafka","optional":false},{"name":"CI/CD","optional":false},{"name":"Docker","optional":false},{"name":"Embeddings","optional":false},{"name":"Java","optional":false},{"name":"Kubernetes","optional":false},{"name":"LangChain","optional":false},{"name":"LLM","optional":false},{"name":"Mistral","optional":false},{"name":"NLP","optional":false},{"name":"OpenAI","optional":false},{"name":"OpenSearch","optional":false},{"name":"pgvector","optional":false},{"name":"PostgreSQL","optional":false},{"name":"Pytest","optional":false},{"name":"Python","optional":false},{"name":"Qdrant","optional":false},{"name":"RAG","optional":false},{"name":"Redis","optional":false},{"name":"Reranking","optional":false},{"name":"Sentence-Transformers","optional":false},{"name":"Spark","optional":false},{"name":"Weaviate","optional":false},{"name":"Transformers","optional":true}],"status":"closed","first_seen_at":"2026-10-04T22:45:09Z","employer_posted_date":null,"last_verified_at":"2026-10-13T11:57:00Z","board_verified":false,"closed_at":"2026-10-13T11:57:00Z","days_open":8,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":8},"description":"1. Collecte, Ingestion & Indexation\n-Pipelines d'ingestion : Concevoir la collecte et le traitement de sources hétérogènes (édition, open data, bases juridiques), le parsing, le nettoyage, le chunking et la normalisation des documents.\n-Indexation & Embeddings : Choisir et industrialiser les modèles d'embeddings, alimenter et maintenir les bases vectorielles, gérer la fraîcheur et la reconstruction des index.\n-Qualité & Volumétrie : Garantir la scalabilité de l'indexation sur des corpus massifs et la traçabilité des données (lignage, versioning des index).\n\n2. Recherche & Pertinence (Retrieval & RAG)\n-Stratégie de retrieval : Combiner recherche lexicale et sémantique (BM25 + embeddings) avec du reranking et du filtrage par métadonnées pour maximiser la pertinence.\n-Évaluation continue : Mettre en place des jeux de tests et des métriques de pertinence (Recall, Precision, nDCG, MRR) pour mesurer et piloter l'amélioration du retrieval.\n-RAG (Retrieval-Augmented Generation) : Structurer la phase de récupération qui alimente les LLM (contexte, citations, dé-duplication, gestion des fenêtres de contexte).\n-Observabilité & Sécurité : Instrumenter les pipelines (logs, métriques, traces) et garantir la conformité des données (RGPD, cloisonnement par pays).\n\n3. Leadership Technique & Gouvernance\n-Culture Craftsmanship : Promouvoir les pratiques de Clean Code, SOLID, et tests automatisés au sein de l'équipe.\n-Rayonnement : Assurer une veille constante et contribuer au rayonnement technique du groupe (articles, meetups, open-source).\nProfil recherché\n-Langages : Python 3.11+ (maîtrise requise), Go (ou appétence Java pour les sujets transverses).\n-Indexation / Vector databases : pgvector, Weaviate, Qdrant, OpenSearch, recherche hybride.\n-Embeddings & NLP : sentence-transformers, tokenisation, parsing de documents.\n-RAG & LLM : LangChain, Reranking, OpenAI, Mistral, Bedrock.\n-Data & Infra : PostgreSQL, Airflow / Spark, Kafka, Redis, Docker, Kubernetes, CI/CD.\n-Tests & Évaluation : Pytest, Frameworks d'évaluation de pertinence.\n-Formation : Diplôme de niveau Master, PhD ou équivalent en Informatique, Data Engineering ou IA.\n-Expérience : Expérience avérée en Data Engineering ou Information Retrieval sur des volumes massifs de données en production.\n-Expertise Retrieval : Vous maîtrisez l'indexation, les embeddings et la recherche hybride, et savez piloter la performance par la data.\n-Culture Tech & Dev : Sensibilité aux pipelines reproductibles, au versioning de datasets, ainsi qu'aux bonnes pratiques de développement (Clean Code).\n-Langues : Anglais fluide indispensable (échanges quotidiens dans un contexte européen).","description_format":"text","description_chars":2651,"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"},{"event":"close","at":"2026-10-13T11:57:00Z"}],"visa":[],"liveness":null,"pay":{"stated_usd_annual":168750,"is_top_pay":false},"html_url":"https://alion.io/job/ouicoding-tech-lead-expert-data-retrieval-rag-hf","json_url":"https://alion.io/job/ouicoding-tech-lead-expert-data-retrieval-rag-hf.json","meta":{"generated_at":"2026-10-13T15:02:29Z","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":22999,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-14T00:00:00Z"}},"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":2940665},"rest":"https://alion.io/mcp/rest/get_company?id=2940665"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fouicoding-tech-lead-expert-data-retrieval-rag-hf"},{"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%2Fouicoding-tech-lead-expert-data-retrieval-rag-hf"},{"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%2Fouicoding-tech-lead-expert-data-retrieval-rag-hf"},{"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/ouicoding-tech-lead-expert-data-retrieval-rag-hf\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fouicoding-tech-lead-expert-data-retrieval-rag-hf"}]}