Sr. AI/LLM Engineer/ Sr. Data Scientist

Emmanuel Obi Obunadike's Portfolio for potential employers

My Projects Contact Me
A description of my image.

I'm a Senior AI/LLM Engineer

I have over a decade of professional experience as a developer. I have delivered major projects for a diverse group of Fortune-1000 companies, across multiple industries such as Consulting (Capgemini – 3 yrs.), Banking (Citi - 2 yrs.), Insurance (The Hartford - 1 yr.), Manufacturing (Boeing – 2 yrs., Cummins - 2yrs.) and Retail (Wegmans – 2 yrs.). My expertise include but not limited to developing and deploying Data Science models such as Forecasting, Supervised and Unsupervised Models, Deep Learning models; engineering Agentic AI models; engineering LLM RAG Models; and engineering Prompt flow.

For your Gen AI needs, LLMs specifically, I can deliver the following:

Production-Grade RAG Pipelines

Design and deploy a complete Retrieval-Augmented Generation (RAG) system tailored to your proprietary data. This involves setting up robust data ingestion from your sources (e.g., databases), creating an efficient vector database, and implementing an optimized retrieval and generation pipeline to provide accurate, context-aware answers while minimizing hallucinations.

Autonomous Agentic Workflows

Identify key business processes suitable for automation and build autonomous AI agents to execute them. By defining specific goals, tools (APIs, databases), and a reasoning framework, I can create agents that handle complex tasks like automated customer support routing, data analysis report generation, or multi-step research inquiries, freeing up your team for more strategic work.

LLM Evaluation & Benchmarking Framework

Establish a systematic framework to objectively measure model performance and ROI. This includes creating golden datasets for testing, implementing metrics like RAGas or ARES for quality assessment, and setting up dashboards to compare the cost, latency, and accuracy of different models (e.g., GPT-4o vs. Claude 3.5 Sonnet) or prompt strategies.

Scalable & Secure API Endpoints

Package your custom AI models and logic into containerized, production-ready APIs. Using technologies like Docker, FastAPI, and Kubernetes, I'll ensure your AI service is scalable, secure, and easily integrated into your existing applications and infrastructure, ready to handle user traffic.

Cost & Performance Optimization

Analyze your entire LLM stack to identify and implement significant cost savings. This includes prompt engineering to reduce token usage, implementing intelligent model routing (using cheaper models for simpler queries), fine-tuning smaller open-source models, and optimizing your vector search and cloud infrastructure for maximum efficiency.

Comprehensive Technical Documentation

Create clear, comprehensive documentation for the AI systems I build. This includes architectural diagrams, API specifications, and operational runbooks, ensuring your team can confidently manage, maintain, and build upon the solution long after my initial engagement is complete.

Skills and Technologies

Programming Languages

Python | SQL | PySpark

AI Engineering Tools

Azure AI Services | Langchain | HuggingFace

LLMs

Chat GPT | Claude | Gemini | Llama | Ollama

Code Versioning

Azure Repos | Databricks Repo | GitHub | GitLab

Data Management (Cloud and On-Prem)

AWS | Azure | Databricks | Hadoop | Hive | Snowflake | Microsoft SQL Server | Oracle

Data Visualization

Power BI | Streamlit | Tableau

Education

  1. M.Sc. Mechanical Engineering

    State University of New York At Buffalo

  2. B.Sc. Mechanical Engineering

    State University of New York At Buffalo

Find me online!