↩ Work / EXPERIENCE

Data Director.Employment

Period: Apr 2025 - Jul 2026
Company: GOZEM ↗
Link: Gozem Data Hub ↗

Owned data platform engineering and internal data products (the Data Hub and 30+ automation tools) and co-led AI strategy across Gozem's footprint, covering Singapore, Togo, Benin, Cameroon, Gabon, and Congo.

Architected and deployed Gozem Data Hub, a centralized platform serving over 650 people (internal employees, field agents, and external partners) with self-service analytics, AI-powered products, and data-driven applications for operations and business decisions.
Built line-of-business and operations apps (driver inspection, invoice extraction, external-acquisition agent performance monitoring, custom dashboard publisher, and others) used daily across Gozem’s operations.
Co-shaped Gozem’s AI strategy and shipped 30+ production automation tools spanning fraud alerts, data extraction, and market monitoring; brought Claude into leadership workflows and onto the product engineering team for coding.
Built observability across 250+ pipelines (Dataform, Airflow, cron jobs) with automated data-quality checks, discrepancy alerts catching incomplete data and duplicates, performance tracking on exceptional events, and a data-exploration MCP.

[•] PROJECTS & USE CASES

6 ENTRIES

Gozem AI Strategy knowledge base

Result 49 validated use cases catalogued; 6 in implementation, with near-full top-management adoption of daily AI assistance.

Problem / Need

Gozem needed a coherent AI strategy spanning operations, logistics, driver management, ecommerce, vehicle financing, customer experience, and fintech, backed by a structured view of the AI vendor and tooling landscape.

Solution

Documented internal AI needs across 9 business units (Transport, Ecommerce, Financing, Finance, Data, Product, Marketing, Operations, Sales) with 50+ stakeholders contributing. Conducted a structured market scan covering 133 tools and vendors across 38 categories: AI vendors, foundation model providers, and automation platforms relevant to Gozem’s stack. Catalogued 49 validated use cases. Built an adoption framework around the 6 moved into implementation: content creation and daily assistance (near-full adoption by top management), coding and code review (rolling out with the product team), classifier and others (in use by the data team). Each use case ships with its agentic workflow architecture.

Tools

Data collection and analysis·Internal stakeholders interviews·Market data scraping·LLM-powered tools profiling·Strategic framework documentation

Gozem Data Hub: Central data & AI workspace

Result 650+ people (employees, field agents, and partners) across 5 countries on one governed platform; 2 onboarded engineers shipped 2 more self-service apps.

Problem / Need

Business and operational teams alongside some external partners across Gozem’s countries lacked a unified workspace for data and AI applications with fast iteration.

Solution

Architected and led development of the Data Hub web app: data exploration environments, data-driven applications, AI-powered tools, operational workflows, and self-service analytics modules. Modeled the micro-services database and platform authentication. Built role-based access governance with 3 access tiers (user, service_admin, platform_admin) crossed with 3 team roles (viewer, worker, manager), supporting over 650 people (internal employees, field agents, and external partners) collaborating across Benin, Togo, Gabon, Cameroon, and Congo. Onboarded 2 engineers who shipped 2 additional self-service apps onto the platform.

Tools

Python·BigQuery·Google Cloud Storage·Cloud Functions·AWS EC2·Docker·RBAC·Claude Code

AI-ready metrics layer & data-warehouse MCP

Result KPI reporting decentralized to business users, removing the data team as the reporting bottleneck; the daily manual checks once needed to confirm generated numbers have nearly disappeared, since AI now produces them grounded and hallucination-free.

Problem / Need

LLM and agentic tools querying the warehouse produced inconsistent or hallucinated KPIs because metric definitions, table sources, and transformation logic were not machine-validated or exposed in a grounded way.

Solution

Built a semantic metrics layer defining validated metrics with their table sources, transformation logic, and canonical queries, exposed through a data-warehouse MCP server, so AI agents generate KPI reports strictly from the layer instead of free-form SQL. Business users self-serve KPI reports with grounding that removes hallucination and the recurring daily verification the data team once owned.

Tools

BigQuery·MCP·Python·Gemini·Claude·Dataform·Metrics/semantic layer

Automated invoice data extraction

Result ~40 hours saved per financing manager per month across thousands of invoices.

Problem / Need

Financing Operations team manually entered data from supplier and operational invoices in multiple formats, slowing reconciliation across Gozem’s multi-country operations.

Solution

Architected and built an automated pipeline ingesting thousands of invoices per month (PDF and image formats) using LLM-powered OCR and document intelligence. Designed an agentic workflow supporting custom schema extraction, with a validation layer flagging anomalies, integrated into Google Sheets for reconciliation. Saved an average of 40 hours per financing manager per month.

Tools

LLM OCR·Document Intelligence·Python·Gemini·Cloud Storage·Google Sheets

RAG-powered customer support chatbot

Result Resolvable support requests handled autonomously; complex cases escalated to Zendesk with conversation summaries preserving context.

Problem / Need

Customer support faced rising request volumes, with human agents spending too much time on resolvable cases and losing context when complex cases needed escalation.

Solution

Oversaw development of a multi-agent Retrieval-Augmented Generation chatbot handling Gozem support requests autonomously, routing resolvable cases to the chatbot and escalating complex cases to Zendesk for complex cases. Added automatic conversation summarization to preserve context for human handoff.

Tools

RAG·Gemini·Vector DB·Python·Zendesk

Real-time market monitoring system

Result +10.2% supply rate, +7.4% request-to-completion, +5.4% coverage at the Vodun Days festival peak (~2,000 users).

Problem / Need

Transportation operations had no live visibility on supply-demand imbalances during high-demand events (public holidays, major urban events), leading to slow operational response.

Solution

Architected a minute-granularity pipeline aggregating GPS, booking, and driver-availability signals. Built supply-demand imbalance detection with threshold-based alerts, plus an operational dashboard surfacing demand-density maps, supply-gap indicators, driver engagement scores, and event KPIs. Implemented automated Google Chat alerts and validated during the Vodun Days festival peak: 10.2% improvement in supply rate, 7.4% increase in request-to-completion rate, and 5.4% coverage gain across ~2,000 distinct users.

Tools

MongoDB·BigQuery·Python·Apache Airflow·Looker Studio·Google Chat API

← Work