Ver categorias
Explorar
Fiverr Pro
Português
$
USD
Younes B
@younes_brg
Senior AI Engineer
França
Francês, Inglês, Árabe
Sobre mim
Senior AI Engineer, 6+ years, focused on generative AI that runs in production: RAG pipelines (chunking, embeddings, hybrid search, re-ranking), multi-agent workflows (LangGraph), LLM-vision OCR and document extraction, plus the observability that goes with it: traces, continuous evaluation, cost/latency trade-offs. Full-stack and cloud end to end: Python/FastAPI, TypeScript/Next.js, GCP, Azure, Kubernetes, Terraform. Recent work: OCR+RAG pipeline for an EventTech startup, production AI engine for two retail brands, document anti-fraud engine for a bank. I lead teams of 2 to 5.
Habilidades
Younes B
offline •
Tempo médio de resposta: 1 hora
Conheça meus serviços
Integrações de IA
I will build a rag chatbot on your documents with sources and evaluation
Portfólio
Experiência profissional
AI Engineer
Naboo • Freelance
Apr 2026 - Jun 2026 • 2 mos
Industrialized an OCR + RAG pipeline for heterogeneous, multi-country supplier documents (quotes, invoices, contracts) at a Series-B EventTech startup. - Multi-agent workflow (LangGraph): extraction, verification, chained actions, with consistency guardrails. - LLM-vision OCR (GPT-4o / Gemini): extraction, classification and checks in one pass on non-standard documents. - Production RAG: semantic chunking, Voyage AI embeddings, hybrid dense+sparse search (Elasticsearch / Qdrant), re-ranking. - FastAPI backend, LangFuse traces, cost/latency optimization; GCP (Cloud Run, BigQuery, CI/CD). Freelance, time & materials, AI team of 4 engineers and 1 PO.
AI Engineer
Rizoa (groupe Mulliez) • Freelance
Oct 2025 - Apr 2026 • 6 mos
Reliability and optimization of a production ML/LLM engine serving two retail brands (Auchan, Kiabi) of the Mulliez group. - RAG: full pipeline rework (chunking, Qdrant HNSW embeddings, re-ranking). - Agents: multi-agent workflows (LangGraph) for chained analyses and actions. - LLM Ops: Langfuse traces, prompt iterations, quality control on a reference question set. - Backend: FastAPI under 500 ms, parallelism, observability. Data: BigQuery / Dataform, Airflow / Cloud Composer DAGs. Freelance, time & materials, AI team.
Lead AI Engineer
DOXALLIA • Freelance
Dec 2025 - Jan 2026 • 1 mo
TrustIA MVP: document anti-fraud engine (PDF analysis, scoring, API) for a Crédit Agricole entity. - PDF analysis: metadata (pikepdf), recompression traces, PAdES signatures (pyHanko), 2D-DOC codes (ZXing). - LLM vision: fast OCR, document classification, consistency of amounts and legal mentions. - FastAPI backend with parallel workers, scoring configurable per business profile. - GCP infrastructure in Terraform: Cloud Run, Cloud SQL, Redis, object storage, GitHub Actions CI/CD. Freelance, fixed price, technical lead.
