Samuel

CHUKWUDI SAMUEL OGBEKILE
Data Engineer · Analytics Engineer · AI / LLM Engineer
[open contact info](look above in the "contact info" section) · [open contact info](look above in the "contact info" section) · github.com/ogbeks · ogbeks.github.io/portfolio ·
upwork.com/fl/~0120d38bac5974a240

PROFESSIONAL SUMMARY

Results-driven Data Engineer, Analytics Engineer, and AI/LLM Engineer with 5+ years of experience designing
end-to-end data pipelines, cloud data warehouses, and large language model evaluation systems. Proven track record of
reducing pipeline costs by 85%, cutting query execution times by 70%, and recovering #60M+ through data-driven
financial analysis. Experienced in prompt engineering, RAG pipeline development, LLM evaluation, and RLHF data
curation across production AI systems. Top Rated Plus freelancer on Upwork with a 100% Job Success Score.

WORK EXPERIENCE

AI Scientist / Trainer
Turing · Contract
Sep 2023 – Present · Remote
• Developed and evaluated LLM outputs across multiple campaigns including function calling API, SWE Benchmark
(GitHub code issue resolution), code evaluation, and long grading, using structured rubrics with defined score thresholds.
• Built and evaluated RAG pipelines for ecommerce clients, writing complex system prompts that explicitly constrained
model responses to provided context only, reducing hallucinations and improving response reliability for invoice and order
management workflows.
• Designed multi-step task workflows to generate high-quality training data, iteratively improving LLM integration accuracy
on sensitive projects requiring maximum evaluation scores.
• Assessed AI model performance using precision, recall, and F1 score metrics, implementing targeted prompt
improvements based on identified failure patterns.

Lead Data Engineer
BuyPower · Full-time · buypower.ng (YC W17)
Sep 2021 – Mar 2024 · Abuja, Nigeria
• Designed and implemented batch and streaming ETL pipelines replicating transaction logs from MongoDB, Firebase, and
MySQL (Amazon RDS) into BigQuery, handling datasets exceeding 150GB and nearly 1 billion rows.
• Led a team of 5 Data Engineers, collaborating with engineering management to improve pipeline architecture and reduce
operational costs by 60%.
• Built DBT-based observability systems reducing time-to-insight from days to seconds across multiple teams, and
implemented query optimization techniques reducing execution time by 70%.
• Automated Looker Studio reporting workflows saving 15+ hours of manual work per week; conducted B2B and B2C
financial analysis recovering #60M+ in outstanding debt.

Data Analytics Engineer (Top Rated Plus · 100% Job Success)
Upwork · Freelance
Sep 2021 – Present · Remote
• Built a GPT-powered application integrating the Amazon Seller API, enabling users to query product details by ASIN and
automatically store promotional records for products rated above 4.5 into a PostgreSQL database.
• Developed end-to-end ETL pipeline migrating 60+ Amazon Seller CSV reports into BigQuery using GCP VM Instance,
Python, FastAPI, and Streamlit backfill UI. (Siturna — private client)
• Reduced Google Cloud Composer 2 pipeline costs by 85%+ through CI/CD implementation with Cloud Build, Cloud
Triggers, and Scheduler. (WebVerif)
• Built ETL pipeline for ~80GB tabular datasets using AWS Glue and deployed XGBoost ML model on AWS SageMaker to
predict NYC taxi prices. (Confidential)
• Delivered analytics solutions for multinational clients using Python, DBT, BigQuery, Metabase, and GitLab; used Claude
Code to build static portfolio sites and interactive quiz applications.
 Data Scientist
Turing.com · Full-time
Jun 2022 – Aug 2022 · Remote
• Built data migration pipelines and ETL processes using Apache Airflow, GCP, and BigQuery, improving data accuracy
and pipeline efficiency.
• Collaborated with cross-functional teams on data QA, and tested ML models providing structured feedback that improved
model efficiency and accuracy.

Data Analyst
Smarterise · Full-time
Apr 2020 – Aug 2021 · Lagos, Nigeria
• Delivered energy consumption and power quality insights reducing clients' annual operational budgets by 30%.
• Built a KPI sales dashboard for a multinational client enabling data-driven decisions that boosted annual sales revenue by
40%.
• Applied ML models to predict energy load profiles for infrastructure research and recommendation purposes.
Python Tutor / Mentor (Part-Time)
Kodland UK · Part-time
Aug 2021 – Feb 2022 · Remote
• Taught Python and Scratch to learners aged 8–17, delivering microlearning-style lessons that built strong programming
foundations with no prior coding experience required.
• Mentored students on applied projects including chatbots, PyGame, Discord/Telegram Bots, and Figma product design.

EDUCATION

MSc, Financial Engineering · 95/100 — Distinction
WorldQuant University · New Orleans, USA
Apr 2020 – Feb 2022 · Relevant: Econometrics, ML in Finance, Portfolio Theory, Computational Finance · Final Project: GARCH
& Markov-Switching Regression on COVID-19 Impact

BSc, Electrical & Electronics Engineering · 4.66/5.0 — First Class Honours
University of Lagos · Akoka, Lagos, Nigeria
Dec 2015 – Jan 2020 · MTN Foundation Scholarship 2018 · First Class Endowment Award 2016, 2017, 2018, 2019

TECHNICAL SKILLS

AI & LLM Prompt Engineering · RAG Pipelines · RLHF · LLM Evaluation · Function Calling API · OpenAI API ·
Claude Code · XGBoost · Scikit-learn · Keras · AWS SageMaker · Hugging Face · Model
Fine-tuning
Data Engineering Apache Airflow · DBT · Apache Kafka · Apache Spark (PySpark) · AWS Glue · Airbyte · Fivetran ·
FastAPI · ETL Pipeline Design · Stream & Batch Processing
Cloud Platforms GCP (BigQuery · Cloud Composer · VM Instance · Cloud Build · Cloud Functions · App Engine) ·
AWS (Glue · S3 · EC2 · RDS · Redshift · SageMaker · Lambda) · Snowflake
Databases BigQuery · PostgreSQL · MySQL · MongoDB · Snowflake · Cloud SQL · Amazon Redshift ·
Supabase · GridDB
Programming Python (Pandas · NumPy · Matplotlib · Scikit-learn · Keras) · SQL · Java · R · C++
DevOps & CI/CD GitHub Actions · Jenkins · GitLab CI · Cloud Build · Terraform · Docker · Linux · Git
Visualization & BI Looker Studio · Metabase · Power BI · Tableau · Mode Analytics · Streamlit · R Shiny · Sigma
Tools & Management Jira · Confluence · Slack · ClickUp · Microsoft Office · Cursor IDE · Amazon Workspace

COMMUNITY SERVICE & ACTIVITIES

• NYSC — SDGs Advocate (Apr 2020 – Feb 2021): Educated and mentored students on the UN's 17 Sustainable
Development Goals and moral values during National Youth Service Corps.
• University of Lagos — Tutor/Mentor (Jan 2017 – Nov 2019): Provided tutorial sessions on difficult engineering courses;
mentored freshers on syllabuses and academic strategies.