💬 Let’s Chat
Tirus Wagacha
Available for full-time roles · Bentonville, AR · Remote-friendly

Hi, I'm Tirus Wagacha.
I build data systems 

Data scientist, backend engineer, and founder. I ship production-grade RAG pipelines, agentic AI systems, and analytics platforms that turn raw operational data into executive-grade decisions.

LlamaIndex LangChain FastAPI Mistral 7B AWS · Docker Power BI PostgreSQL
See Featured Work → Get in Touch
4+
Years building data systems
10+
Shipped projects
4.0
GPA · M.S. Data Analytics
6
Industries served

About Me

Tirus Kimani Wagacha

I am a data scientist and software engineer focused on building intelligent, data-driven systems that deliver measurable business impact. My work sits at the intersection of scalable backend engineering, machine learning, and generative AI. I design systems that automate insight generation, reduce operational friction, and empower data-driven decision-making.

I hold a Master of Science in Data Analytics-Data Science from Kansas State University (GPA: 4.0) and bring hands-on experience across fintech, logistics, and insurance domains. My core strengths include building LLM-powered agents, NLP pipelines, and self-serve analytics platforms, as well as deploying production-ready solutions that scale reliably.

I enjoy translating complex data into clear, actionable intelligence and building systems that help organizations move faster, smarter, and with confidence

Download Resume See Projects

Chat with Me

Ask about my work, projects, or how I build intelligent systems.

Experience

4+ years building data-driven backend platforms and AI systems across logistics, supply chain, fintech, insurance, oil & gas, and pharma.

Data Analytics Graduate Teaching & Research Assistant
Aug 2024 – Jan 2026
Kansas State University · Manhattan, KS
  • Led end-to-end statistical modeling for a research study on blockchain-based verification systems in pharmaceutical supply chains, turning raw survey data into policy- and operations-grade insights.
  • Designed Python preprocessing and aggregation pipelines benchmarking Data Analytics programs nationally, directly informing faculty planning and curriculum decisions.
  • Supported instruction in Python, SQL, and data visualization, reinforcing real-world analytics best practices.
Analytics & Backend Developer
Dec 2022 – Aug 2024
Volane International · Nairobi, Kenya
  • Designed an Inventory & Distribution Management System for oil & gas downstream that integrated transactional data, predictive analytics, and reporting workflows — reducing stockouts by 30% and improving demand-forecast accuracy.
  • Engineered SQL and MongoDB pipelines feeding executive Power BI dashboards for real-time KPI visibility across supply chain operations.
  • Implemented CI/CD and containerized deployments using Docker and Kubernetes on AWS, improving release velocity and system reliability.
Software Developer
Mar 2022 – Nov 2022
MPost · Nairobi, Kenya
  • Re-engineered a multitenant virtual addressing and last-mile logistics platform integrating NoSQL databases, Databricks, digital payments, and reporting workflows — lifting service adoption and delivery efficiency.
  • Optimized SQL queries and indexing strategies, reducing database response times by 25%.
  • Automated customer support and data capture using chatbots and USSD applications; conducted EDA to surface operational bottlenecks.
Backend Software Developer
May 2020 – Nov 2022
Nanatec Limited · Nairobi, Kenya
  • Built insurance SaaS platforms using Domain-Driven Design and microservices, supporting policy administration and claims processing workflows.
  • Designed Tableau and SQL-based dashboards visualizing claims trends, policy performance, and operational KPIs.
  • Implemented optimized schemas with strong transaction management and error handling for high-integrity insurance workflows.
Engineering Internships
2019 – 2021
Maniwa Technologies · KTDA-Chai Trading Company · Kenya
  • Maniwa Technologies (2021): ATM, CDM, currency-counter, and electronic-safe maintenance and diagnostics across live banking sites.
  • KTDA-Chai Trading (2019): Hydraulic forklifts, generators, and warehouse conveyor maintenance; welding and fabrication.
  • The mechanical-engineering grounding that still shapes my systems-thinking approach to data and software today.
Founder & Innovation Lead — TITEK Innovate & Consulting

Building AI-powered, data-driven products across property management, healthcare, travel, agriculture, insurance, and supply chain.

Skills & Technologies

Engineering-grade data, AI, and backend systems — from raw pipelines to hosted, agent-driven products.

Python
Python

Pandas, NumPy, scikit-learn, PySpark, asyncio. ETL pipelines, ML workflows, and agent logic.

SQL
SQL & NoSQL

PostgreSQL, MySQL, MongoDB. Schema design, query optimization, and indexing for production workloads.

Machine Learning
Data Science & ML

Statistical modeling, KMeans, classification, regression, forecasting. SAS, Databricks, scikit-learn.

Data Visualization
BI & Visualization

Power BI, Tableau, Plotly, Matplotlib. Executive dashboards and narrative-driven insights.

LLMs & RAG

LlamaIndex, LangChain, hybrid BM25+vector retrieval, cross-encoder reranking, citation-required prompting.

Agentic AI

LangGraph, Smolagents, tool/function calling, multi-LLM orchestration with judge arbitration.

Backend & APIs

FastAPI, Express.js, REST design, auth, audit logging, maker-checker controls, double-entry accounting.

Cloud & DevOps

AWS, Docker, Kubernetes, Nginx, CI/CD, Hugging Face Spaces. WSL2 + CUDA for local LLM hosting.

Selected Projects

Real-world solutions combining data, AI, and systems engineering.

Pharma Document Intelligence RAG
RAG + GenAI
Featured
Pharma Document Intelligence: Grounded RAG for Regulated Docs

Production-grade Retrieval-Augmented Generation pipeline for pharmaceutical documents. Combines hybrid BM25 + semantic vector search, cross-encoder reranking, and a locally-hosted Mistral 7B LLM to deliver page-cited, grounded answers across Certificates of Quality, BSE/TSE declarations, and packaging specs — with OCR fallback for scanned PDFs and automatic page-level classification.

View Code Live Demo
Retail Order Cancellation Intelligence dashboard
ML + Analytics
Featured
Retail Intelligence: Order Cancellation Analytics

An investigative analytics platform built on FastAPI + Streamlit + React that turns a retail cancellation workbook into a filter-aware, multi-tab experience. Five LLM-backed AI surfaces (multi-model chat with judge arbitration, narrator, recommender, and dynamic suggestions) surface non-obvious findings — including that 14.5% of cancels are for since-discontinued SKUs — while numeric facts stay in deterministic Python with a full fallback path.

View Code Live Demo
Sales KPIs Dashboard
Power BI
Analyzing Sales Data

Designed and developed a comprehensive KPI dashboard in Power BI to track critical business metrics across multiple dimensions including sales performance, product categories, geographic distribution, and channel effectiveness.

Read Article
Subsidy Project
Tableau
Analyzing Subsidies & Emergency Support for Livestock

Explored government agricultural subsidy distribution across Kansas, Nebraska, and Oklahoma to surface inefficiencies and strategic positioning for livestock farmers using Tableau.

Read Article
Amazon Pricing
Data Storytelling
The Pricing Dilemma on Amazon

Investigated discount strategy effects on customer trust and engagement, balancing perceived value and ratings using Amazon sales data.

Read Article
Comparing Writing Style Across Reuters Regions
NLP + ML
Comparing Writing Styles: Regional Variation Between U.S. and European News Articles

Project to extract, clean and analyze writing style differences between Reuters articles by region (US vs Europe). The analysis pipeline extracts articles, computes linguistic features (POS,Sentiment, Embeddings), runs topic modeling and classification, and outputs CSVs and per-article text files.

View Project
Recommender System
NLP + ML + GenAI
Semantic Question Extraction & Template Builder for Survey Optimization

This project automates consolidation of disparate historical survey questions into a concise, validated generic survey template. It combines semantic embedding similarity, clustering and topic modeling, and human-in-the-loop review with LLM-assisted paraphrasing to produce high-quality, reusable questions and an Interactive Streamlit Dashboard.

View Project
Recommender System
NLP + ML
Sentiment-Enhanced Product Recommender System

A sentiment-enhanced recommendation system was built using fine-tuned BERT models on SST-5 for sentiment analysis and FAISS for similarity searches. It combines sentiment scores from customer reviews with product embeddings to deliver tailored recommendations.

View Project
Customer Feedback Analysis
Text Analytics
Customer Feedback Analysis for Hospitality

Analyzed hotel reviews to help AfriDusky Tours & Travel Agency enter the Kenyan market with customer-centric insights on satisfaction, strengths, and improvement areas.

View Project
Forte Hotel Conjoint Analysis
Preference Modeling
Conjoint Analysis: FORTE Hotel Design

Identified preferred hotel design attributes and trade-offs using conjoint analysis to inform user-centered hospitality design decisions.

View Project
Data Job Market Analysis
Market Research
Data Job Market: SQL

Explored demand and compensation trends in the data analytics job market, focusing on high-growth roles and skill salary alignment.

View Project
See More Projects

Get in Touch

Whether you're interested in collaboration, roles, or just want to chat about intelligent systems, drop a message.

Reach Out Directly

Email: kimtirus@gmail.com
Phone: +1 603-377-2469

LinkedIn GitHub

© Tirus Kimani Wagacha. All rights reserved.