Asil Abduldaem

Tripoli, Libya · Open to opportunities

Asil
Abduldaem

AI & Digital Transformation Engineer

I build AI systems, forecasting models and data platforms for the people running oil & gas operations.

Selected work Download CV

Operational data → engineering answers

ACE Oil & Gas welcome screen with engineering lenses, suggested production questions and a natural-language input ACE — AI Chat EngineView screenshot
Product screenshot · Oil & gas edition

01 About

From field operations
to data systems

At PETGO — Petro Engineering and Technical Group, an oil & gas services group in Libya, I build forecasting models, database agents and the operational tools that replace paper workflows.

My work connects the data layer to the person using it: engineers asking questions in Arabic and English, supervisors tracking permits, and leadership reading production reports.

Alongside that, I design data platforms. At Presto, that means an AWS lakehouse connecting four source systems through CDC ingestion, Step Functions and tested dbt marts.

I care about what happens after delivery: tests, monitoring, reversible changes and documentation that lets another engineer take ownership.

Years in oil & gas
2+
Operational units served
5
Presto source systems
4

02 Experience

Where I do the work

PETGO — Petro Engineering and Technical Group

AI & Digital Transformation Engineer

Dec 2024 — Present
  • Built ML well-production forecasting on historical production, well-test results and reservoir properties, replacing manual estimates in planning and reporting.
  • Deployed ACE, an LLM agent platform with Arabic and English NLP, letting engineers query operational databases without SQL — with RAG and vector search over internal documents.
  • Developed voice AI agents for hands-free data retrieval and reporting in field environments.
  • Designed a digital work-permit platform that replaced paper approvals with live status updates and supervisor notifications.
  • Built an internal talent evaluation platform in Next.js, React and PostgreSQL, standardising technical assessment and candidate tracking.
  • Delivered Power BI executive dashboards across 5 operational units with automated refresh.

PETGO — Petro Engineering and Technical Group

Data Analyst — Oil & Gas

May 2024 — Nov 2024
  • Worked across the company's production and well-test data systems to monitor well performance and support engineering analysis.
  • Maintained and improved allocation logic and rules distributing production to individual wells and facilities.
  • Cleaned, validated and organised large volumes of production and well-test data underpinning reports and models.
  • Built Power BI reports surfacing trends, anomalies and underperforming wells for engineers and managers.

Presto — Food Delivery

Data Engineer

Present
  • Architected an AWS medallion lakehouse (S3 + Redshift) unifying four source systems — MySQL, Odoo/PostgreSQL, MongoDB and BigQuery — into one governed warehouse.
  • Moved analytical workloads to Redshift with Glue batch and DMS change-data-capture ingestion, separating reporting from the production database.
  • Stopped ongoing permanent loss of clickstream history with a daily BigQuery → S3 archival pipeline and lifecycle tiering.
  • Built a dbt project from staging through marts with automated tests and shared business-metric definitions.
  • Implemented Step Functions orchestration with retry logic and CloudWatch/SNS alerting, making pipeline failures visible through automated alerts.
  • Moved all pipeline code into Git with Terraform/CloudFormation IaC and GitHub Actions CI/CD, replacing console-edited scripts.

03 Selected work

The systems, up close

Eight projects across AI, data infrastructure and operational software. Select a preview to see the full image.

01AI systems · Oil & gas / Financial services

ACE — AI Chat Engine

A multi-tenant LLM agent platform for production engineers and analysts. A LangGraph agent queries PostgreSQL, MySQL and SQL Server in Arabic and English, with a read-only query guard. Each department connects its own database and LLM provider.

Document analysis, voice input and output, generated reports and five-tier role-based access. Oil & Gas and Financial editions share one codebase.

Operational data → engineering answers

  • LangGraph
  • LangChain
  • MCP
  • FastAPI
  • Anthropic / OpenAI / Gemini
  • PostgreSQL
  • Qdrant
  • RBAC
ACE Oil & Gas welcome screen with engineering lenses, suggested production questions and a natural-language input ACE — Engineering workspaceView screenshot
Product screenshot · Production questions, engineering analysis and reporting in natural language
ACE Financial welcome screen with credit risk, financial analyst and treasury lenses and suggested analysis questions ACE — Financial workspaceView screenshot
Product screenshot · The same platform, tailored to financial analysis, credit risk and treasury

02Machine learning · Energy

ML well production forecasting

Predicts well output from historical production, well-test results and reservoir properties. The models feed planning and reporting cycles that previously relied on manual estimates.

Well history → production forecasts

  • Python
  • scikit-learn
  • PostgreSQL
  • Power BI

03Data engineering · Food delivery

Presto — Lakehouse migration

Presto ran analytics against its production database and deleted clickstream history to stay within a storage cap. I designed and delivered a medallion lakehouse connecting MySQL, Odoo/PostgreSQL, MongoDB and BigQuery.

S3 preserves raw history; Redshift holds curated models and dbt marts with shared metric definitions. Glue and DMS handle ingestion, with Step Functions orchestration, automated tests and failure alerts.

Four source systems → shared business metrics

  • AWS Glue
  • DMS (CDC)
  • Redshift
  • S3
  • dbt
  • Step Functions
  • Terraform
  • PySpark
Four source systems flow into S3 Bronze history, Redshift Silver models and dbt Gold marts for analytics Presto — From source systems to analyticsView architecture
Architecture illustration · Simplified from project documentation; this is not a live monitoring screen

04Internal tools · People & projects

PETGO Pulse

An intranet for project and contribution tracking, accounts, performance cycles and notifications. It brings HR and project reporting together, with light and dark themes, a shared design system and tests across the frontend and backend.

Team contributions → project visibility

  • Django 5
  • DRF
  • React
  • TanStack Query
  • Tailwind v4
  • PostgreSQL
  • pytest
  • Vitest

05Voice interfaces · Field operations

Voice AI field agents

A hands-free interface for retrieving field readings and logging reports through spoken commands. Built for field work where using a keyboard is impractical.

Spoken requests → field data

  • Python
  • Whisper
  • TTS
  • n8n
  • REST

06Operational systems · Approvals

Digital work permit platform

Replaced paper permit-to-work approvals with a digital workflow. Approval chains, live status updates, supervisor notifications and an auditable history keep each permit traceable.

Paper permits → tracked approvals

  • Next.js
  • PostgreSQL
  • REST
  • Docker

07Internal tools · Assessment

Talent evaluation platform

Structured technical assessments and candidate tracking, giving departments a shared rubric for evaluating candidates and staff.

Technical assessments → consistent evaluation

  • Next.js
  • React
  • TypeScript
  • PostgreSQL

08Business intelligence · Leadership

Executive BI dashboards

Production, finance and HR reporting across five operational units. Automated refresh cycles replace hand-assembled monthly decks with current data for leadership.

Operational records → management reporting

  • Power BI
  • DAX
  • SQL
  • ETL

04 Capabilities

What I work with

AI systems & agent engineering

  • Natural-language → SQL agents
  • Read-only query guardrails
  • LangGraph state machines
  • Agent memory & checkpointing
  • Model Context Protocol (MCP)
  • Tool-calling & function schemas
  • Provider-agnostic LLM abstraction
  • Multi-tenant agent isolation
  • RAG & embeddings
  • Vector search
  • LLM observability (LangSmith)
  • Prompt & persona systems
  • Voice agents (STT / TTS)
  • Arabic & English NLP

Data platforms & modelling

  • Medallion architecture
  • Lakehouse design (S3 + MPP)
  • OLTP / OLAP workload separation
  • Change data capture (CDC)
  • dbt: staging → intermediate → marts
  • Dimensional modelling & grain
  • Surrogate keys & SCDs
  • Incremental models
  • Metric standardisation
  • Source-freshness SLAs
  • Reconciliation testing
  • Idempotent, replayable pipelines
  • Schema-drift handling
  • Redshift sort / dist keys

Cloud & infrastructure

  • S3
  • Glue / PySpark
  • Redshift
  • DMS
  • Step Functions
  • Athena
  • CloudWatch / SNS
  • Terraform
  • CloudFormation
  • Docker
  • GitHub Actions
  • Linux / VPS

Governance & security

  • Least-privilege IAM
  • Role-based access control
  • SSO federation (SAML)
  • Secrets management
  • PII anonymisation
  • Audit logging
  • Data catalog & lineage
  • Runbooks & DR procedures

Databases

  • PostgreSQL
  • MySQL
  • SQL Server
  • MongoDB
  • Redshift
  • BigQuery
  • Qdrant
  • Supabase

Backend & APIs

  • Python
  • SQL
  • FastAPI
  • Django / DRF
  • Flask
  • SQLAlchemy
  • Pydantic
  • Async & SSE streaming
  • C#

Frontend

  • TypeScript
  • React
  • Next.js
  • Tailwind
  • TanStack Query
  • Vite

Analytics & ML

  • Power BI / DAX
  • Metabase
  • Production forecasting
  • Feature engineering
  • Model evaluation
  • Jupyter

Engineering practice

  • Test-covered services
  • CI gates on PR
  • Infrastructure as code
  • Trade-off analysis & ADRs
  • Phased migration roadmaps
  • Technical writing

05 Contact

Have a system
worth building?

Open to roles and collaborations in data engineering, AI systems and digital transformation. Based in Tripoli; open to remote work.

aseeldayem16@gmail.com
GitHub LinkedIn Download CV Tripoli, Libya

Open full image