Albert Dulout

Applied AI Engineer in Singapore: Data Scientist by title, engineer by scope.

I build document-intelligence and optimisation systems from prototype to production on Azure, frequently as the sole engineer owning the full path from data to deployment, turning ambiguous operational problems into dependable software.

Outside work: rugby, long-distance running and cooking.

Built 4 enterprise AI pilots; the selected one became a company-wide MVP
2 platforms live in production, built and run solo
Microsoft Certified: Azure AI Engineer Associate

Email me Download résumé

Selected work

Enterprise AI, public-sector ML, operations research, internal platforms and a live public product.

One of four document-review pilots became a company-wide MVP

Enterprise client · property and real estate · 4 PoCs · 2025

Built the backend, AI pipelines and Azure foundations for four rapid enterprise document-review PoCs. The HR-screening pilot cut internship-candidate ranking from half a day to minutes; I anonymised candidate data to reduce identity bias and randomised candidate order to test ranking consistency. One PoC was selected for a company-wide MVP and handed to the delivery team. Across the workflows, 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 workflow. Produced annotated PDFs, clause trackers, ranked candidate reports and Excel exports so reviewers could inspect findings against the source material.

Real-time urban visualisations for a national planning exhibition

Urban Redevelopment Authority · public exhibition · 2024–2025

Built the interactive generative-AI exhibit for Enabling Sustainable Growth: Shaping the Future of Work, part of URA’s Draft Master Plan 2025 public engagement. Visitors selected amenities and design features on a tablet and received real-time visualisations of possible future business nodes. Launched by the Senior Minister of State for National Development and Digital Development and Information, the exhibition then ran free to the public at The URA Centre for ten weeks.

Stage: Public exhibition · 24 Oct 2024–3 Jan 2025
Delivery: ~10 days to build
Constraint: ~10-second generation target

Built with. Python, state-of-the-art image-generation models, LoRA fine-tuning, model-based upscaling and a tablet-facing interactive front end.

Coverage. URA press release · PALO IT project announcement

How the visual style stayed consistent

Style development. Generated several hundred candidate images across keyword combinations, then trained a LoRA on the images chosen by URA’s architect so live output held one coherent visual style rather than drifting between visitors.
Latency. Generated at reduced resolution and upscaled the output with a separate model, holding the interaction inside a ten-second budget so visitors saw their visualisation while still standing at the tablet.
Constraint. Built in about ten days ahead of a fixed public launch date.
Live support. Supported the installation across its ten-week public run, including on-site visits to diagnose and fix faults while the exhibition stayed open.

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 turned inconsistent client workbooks into validated scenarios for about 40 stops and delivered a data-quality assessment identifying the gaps the client needed to close before benchmarking against their manual baseline. The solver modelled capacity, service time, shifts, depots and unloads, and returned unserved stops when a scenario was infeasible.

Scope: ~40 stops per scenario · 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. Shipped a moving-average baseline behind a swappable forecasting interface, so Prophet or XGBoost models can drop in without touching the API.

Removing monthly timesheet and billing work for HR and Finance

Internal production platform · PALO IT · 2026

Built and deployed a governed Azure data platform that synchronised workforce and finance data into PostgreSQL. It replaced a recurring monthly reconciliation that consumed roughly a person-day across two teams, ending manual timesheet follow-up and spreadsheet-based billing-exception overrides. Checkpoints, completeness gates and role-based access groups protected data integrity and access.

Stage: Internal production
Outcome: ~1 person-day of monthly reconciliation removed
Ownership: Sole engineer · ~3 months

Built with. TypeScript, Azure Functions, Durable Functions, PostgreSQL, Drizzle, Entra ID, Bicep, Power Automate, 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.
Finance access. Built finance-facing views and role-scoped read APIs that replaced manual exception calculations, plus an MCP interface for workforce queries.
HR workflow. Diagnosed incomplete timesheets as the recurring root cause and specified an automated reminder flow on the governed data, implemented in Power Automate by a colleague.
Development and access. Built a mock API server for the development environment and kept its dataset synchronised with production. I also set up a GitHub-based ticket workflow for access requests.

Digitising 400+ family recipes

Live personal platform · 2026–present

Open live demo

Built and now operate a live public platform holding 400+ recipes digitised 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.

Stage: Live · 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 catalogue 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

Delivering applied AI and cloud systems since 2023, 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

Built a self-service Azure Dev Center catalogue for Container Apps, PostgreSQL, Static Web Apps and AI/RAG services. Bicep, managed identities, scoped RBAC and GitHub OIDC let developers provision guarded environments without subscription-level access and enabled a designer to ship AI-assisted mockups without touching the underlying Azure infrastructure.
Delivered applied AI systems across document intelligence, forecasting, optimisation 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.
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 Optimisation

IMT Atlantique · France · 2019–2023

Five-year French engineering curriculum combining advanced mathematics with applied machine learning and operations research.

Preparatory Class for the Grandes Écoles

Lycée Montaigne · Bordeaux · 2016–2019

Intensive mathematics and physics programme for France’s competitive engineering-school entrance exams.

Credential. Microsoft Certified: Azure AI Engineer Associate
Languages. French (native) · English (professional) · Spanish (conversational) · Russian (intermediate)

About

Rugby. Two-time Singapore Development League champion.
Running and strength. Long-distance running and strength training.
Cooking and diving. Digitising my family’s recipes and scuba diving as a PADI Advanced Open Water Diver.