Albert Dulout

Albert Dulout

Applied AI engineer in Singapore.

I build document-intelligence and optimization systems from prototype to production—usually on Azure, often as the engineer owning the whole path.

Outside work: rugby, long-distance running and digitising my family’s recipes.

Email me Download résumé

Selected work

Four systems, each with a different problem and delivery path.

Four document-review pilots built under tight deadlines

Enterprise client delivery · 4 PoCs · 2025

Built the backend, AI pipelines and Azure foundations for four rapid enterprise document-review PoCs. One was selected for a company-wide MVP, with the architecture handed over to the delivery team. Reviewer outputs preserved source text or page references for verification.

Stage
4 PoCs · 1 selected for company-wide MVP
Delivery
~2 weeks per PoC
Team
2 engineers · 1 designer

Built with. Python, FastAPI, Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure AI Document Intelligence and Vision OCR, API Management, Container Apps, Static Web Apps, Docker and GitHub Actions.

How review stayed verifiable
  • Backend and AI. Designed FastAPI services and AI pipelines for OCR, parsing, embeddings, hybrid retrieval and schema-constrained comparison. I also owned API management, container deployment and CI/CD, while teammates built most React interfaces.
  • Regulatory comparison. Used exact and fuzzy prefilters before batched LLM verification.
  • Loan review. Combined hierarchical chunks, BM25, HNSW vector search and semantic reranking.
  • Reviewer outputs. Produced annotated PDFs, clause trackers, ranked candidate reports and Excel exports.

Routing waste collection across two countries

Client delivery · Operations Research · 2025

Delivered a waste-collection planning platform in about six weeks for operations across two countries. As sole engineer, I built a solver that modelled capacity, service time, shifts, depots and unloads, and returned unserved stops when a scenario was infeasible.

Scope
Operations across 2 countries
Delivery
~6 weeks
Team
Sole engineer

Built with. Python, FastAPI, Google OR-Tools, React, pandas, OSRM, Google Routes, Docker and Azure Container Apps.

How routing constraints worked
  • Solver. Modelled capacity, service time, shifts, depots, unloads and objectives including time, distance, cost, coverage and profit.
  • Repeat trips. Represented repeat trips with shift-aware virtual vehicles.
  • Distance matrices. Supported Haversine, cached OSRM and Google route matrices to balance road realism, cost, rate limits and offline operation.
  • Operational workflows. Owned the FastAPI backend and React interface, including tolerant XLSX/CSV parsing and PDF/XLSX reports.
  • Forecasting extension. Implemented a moving-average baseline behind a replaceable forecasting interface designed for future Prophet or XGBoost models.

One governed data layer for HR, Finance and Audit

Internal production platform · PALO IT · 2026

Built and deployed a governed Azure data platform that synced workforce and finance data into PostgreSQL for Internal, HR, Finance and Audit users. Checkpoints, completeness gates and role-based access groups protected data integrity and access.

Stage
Internal production
Scope
10 sync domains · 4 role-based access groups
Ownership
Sole engineer · ~3 months

Built with. TypeScript, Azure Functions, Durable Functions, PostgreSQL, Drizzle, Entra ID, Bicep, GitHub Actions OIDC and Azure Monitor.

What production required
  • Azure ownership. Owned the platform from infrastructure design through production deployment, provisioning dev and production resource groups, Functions, PostgreSQL, Key Vault and monitoring with Bicep.
  • Access control. Created Microsoft Entra security groups for Internal, HR, Finance and Audit access, then configured managed identities and scoped RBAC for runtime and deployment.
  • Data reliability. Used Durable Functions to coordinate ten sync domains; checkpoints and completeness gates allowed interrupted imports to resume safely without treating partial source data as deletions.
  • Interfaces. Built role-scoped read APIs and an MCP interface for workforce queries.

Digitising 400+ family recipes

Public personal project · 2026–present

Open live demo

I operate a public collection of 400+ recipes from scanned documents and phone photographs. The French-first platform adds English translation, search, a recipe-aware assistant, nutrition estimates and protected review workflows while keeping most infrastructure within Cloudflare's free tiers.

Public proof
400+ published recipes
Operations
Scheduled Dropbox ingestion
Ownership
Sole builder and maintainer

Built with. React, TypeScript, Cloudflare Pages and Functions, D1, Vectorize, R2, Queues, Gemini, OpenAI Image 2 and GitHub Actions.

Mathilde Recipes gallery showing recipe photographs, search and category filters.
Live French-first recipe gallery and recipe-aware assistant
How the publishing pipeline works
  • Ingestion. Extracts text or image content and requests structured model output.
  • Quality controls. Validates provenance and tags, then removes mirrored and fingerprint duplicates.
  • Publishing. Rebuilds a deterministic catalog and records skip reasons and validation failures instead of silently publishing.
  • Asynchronous operations. Uses queued image generation and protected admin routes to separate long-running and review-sensitive work from the public request path.

Experience

3+ years delivering applied AI and cloud systems, preceded by analytics roles at Papernest and Nestlé.

PALO IT

Singapore

Data Scientist, Innovation Lab
February 2025–present
Junior Data Scientist
March 2023–January 2025
  • Delivered applied AI systems across document intelligence, forecasting, optimization and cloud data platforms from technical discovery through deployment and handover, primarily on Azure. Also worked on AWS, including GCC environments.
  • Built and evaluated cash-flow forecasting models during a one-month project using PyTorch, with MLflow for experiment tracking and model comparison.
  • Applied LoRA fine-tuning in separate projects and served open-source models with Hugging Face Text Generation Inference.
  • Created a reusable Azure Dev Center catalog and Vercel-style self-service deployment path for Container Apps, PostgreSQL, Static Web Apps and AI/RAG services. Bicep, managed identities, scoped RBAC and GitHub OIDC made delivery repeatable and enabled a designer to publish AI-assisted mockups without managing the underlying Azure infrastructure.
  • Translated client needs into technical options and proposals, sized delivery teams and infrastructure, and mentored Innovation Lab engineers.

Analytics Engineer Intern

Papernest · Barcelona · February–August 2022

  • Increased successful Google Ads conversion imports by 6% by tracing and restoring records dropped across BigQuery-based SQL and ETL pipelines.
  • Automated campaign alerts and maintained reporting used for weekly spend decisions.

Master Data Analyst Intern

Nestlé Europe · Paris · June–December 2021

  • Built an Excel/VBA pricing simulator on SAP and SQL data so commercial teams could test scenarios independently; also automated recurring data-management work.

Education and credentials

Engineering Degree / MSc, Data Science and Optimization

IMT Atlantique · France · 2019–2023

Coursework included machine learning, computer vision, natural language processing, time-series forecasting, operations research, optimization algorithms and big-data architecture.

Preparatory Class for the Grandes Écoles

Lycée Montaigne · Bordeaux · 2016–2019

Intensive preparation in mathematics, physics and chemistry for the competitive entrance examinations to French engineering schools.

Beyond the work