Open to opportunities

Stephen Hambo

@stephenhambo

Message

Data engineer at YRCS building LLM retrieval pipelines and preparing Llama 3.1 data for fine-tuning.

United States

Message

What I'm looking for

I'm seeking Data Engineering and AI Engineering roles.

At YRCS, I built Python data pipelines for financial-domain LLM applications, preparing data for QLoRA fine-tuning of Llama 3.1 8B Instruct and implementing model evaluation and vLLM deployment.

I also developed ingestion and retrieval pipelines for a customer-service agent with Tool Calling, including hybrid full-text and pgvector search. For a RAG QA system, I implemented document processing and retrieval with LangChain, FastAPI, FAISS, and OpenAI APIs.

At Insight Global, as a contractor at Experian, I developed AWS data pipelines and orchestrated incremental ETL with Airflow/MWAA. I also contributed to streaming ELT with Kafka and Spark Structured Streaming, and worked on Redshift performance, data quality, and production support.

Experience

Work history, roles, and key accomplishments

Data / AI Engineering Consultant

YRCS

Jan 2026 - Sep 2026 (8 months)

Built Python-based data pipelines for financial-domain LLM applications, including dataset ingestion, cleaning, and preparation for QLoRA fine-tuning of Llama 3.1. Developed ingestion and retrieval pipelines for an LLM customer-service agent with tool calling and hybrid search.

Python LLM RAG QLoRA LLaMA 3.1 VLLM Lang Chain fastAPI Faiss Pgvector Tool calling Data Pipelines

Data Engineer

Insight Global

Oct 2023 - Dec 2025 (2 years 2 months)

Implemented data infrastructure and ETL pipelines on AWS, including Redshift, S3, Lambda, and EMR. Performed DBA tasks, performance tuning, and provided production support.

AWS Redshift S3 Lambda EMR PySpark Airflow AWS MWAA DMS Kafka Spark Structured Streaming Iceberg DBT Athena Glue Git GitHub Actions Cloudwatch SNS PowerShell Agile Documentation

Data Engineer Intern

Global Technology Specialist Company

Jan 2023 - Mar 2023 (2 months)

Built PySpark and SQL ETL pipelines on Databricks and Snowflake for data ingestion and transformation. Developed Azure Data Factory pipelines and Tableau dashboards for BI reporting.

PySpark SQL Databricks Snowflake Azure Data Factory Tableau ETL