Uche Ogbuji

Data Analyst • Full-stack Engineer • Boulder, CO, US

Public Speaking

DevOps

Big Data

SQL

Cloud Development

REST

API

Start-ups

Database Design

Technical Consultancy

Writing

Poetry

Music Production

GraphQL

Graph Databases

XML

Linux

Data Analysis

Data Processing

Data Mining

Machine Learning

PyTorch

Python

Available for hire fromNegotiable

Contracts

Data & software engineer and lead / IT architect (30 years' experience)…also poet/editor, DJ/composer, public speaker & performer

Engineering leader nurturing diverse teams to drive data innovation and systems architecture. History as consultant, founder & CTO. Electronic/Computer Engineer by education (in Nigeria and the US). Expert and pioneer in data architecture, distributed systems and open source software. Over 300 tech articles in industry journals. Contributed to Python's initial XML implementations. Also a poet, spoken word performer & DJ with 2 award-winning poetry books; work fusing Igbo culture, European classicism, American Mountain West setting, Hip-Hop and afrofuturism. Born in Calabar, Nigeria, settled near Boulder, Colorado after much world wandering. Snowboarding, longboarding, coaching & playing soccer, listening to & making music, dancing.

Projects

Toolio platform for Private AI/Large Language Model Agents

Created a platform, Toolio, to run private Large Language Model (LLM) agents and tool-calling workflows on Apple Silicon, and also to constrain LLM output to a JSON schema, enhancing usability & inference speed. Problem Generative AI can be difficult to steer for controlled workflows, such as custom API Integration. It can also be hard to integrate such API usage (tool-calling) in a single, private platform, which is required e.g. for health-care and CRM needs. My Contributions Used my extensive AI/Machine Learning & Python programming experience to take a steering library for the output, and form it to API/tool requests based on the user query. This involved designing am async REST API, implemented via FastAPI, incorporating OpenAI/GPT-style tool-calling flow. Outcomes Toolio immediately garnered much interest (30 GitHub stars in 24 hours) from people facing the same output control and tool-calling needs, an area poised to unleash the keenest innovations. See More

Oori Buddies: LLM-powered social chat persona bots

Oori Buddies is an entertainment product for chat communities which provides personas which can interact with users in order to enhance and expand interactions among those users themselves. The overarching goal is to use AI technology to seed and catalyze richer human communities online. Oori Buddies is launched for Discord. Oori Buddies includes features such as Oori Pets which provide gaming-like incentives for interacting with Oori Buddies. The technology uses advanced AI/LLM features such as flat and hierarchical retrieval augmentation (RAG), few-shot prompting, model fine-tuning, multi-expert (model) multiplexing, reasoning/action, asynchronous orchestration, and more.See More

OgbujiPT: Python toolkit for Artificial Intelligence processing workflows

Open Source toolkit for using self-hosted AI/large language models (LLMs), but also with support for full-service such as ChatGPT. Includes demos with RAG ("chat your documents") and AGI/AutoGPT/privateGPT-style capabilities, via streamlit, Discord, web apps, command line, etc. Helper functions for common LLM tasks, such as those provided by projects such as langchain, but not as extensive. This is by design; OgbujiPT emphasizes simplicity and transparency.See More

Internal AI/Knowledgebase Chatbot

Consultant Solution Architect and Software Engineer at Innovation Refunds (Financial Services / Fintech). I developed a custom chatbot to resolve queries of internal users, utilizing a Knowledgebase maintained in Contentful CMS. Challenge was to create a system that could answer questions and offer suggestions in the fintech domain using a trove of documents and data. The pre-existing process was inefficient and ineffective. As the engineering lead, I also applied skills in AI, Python in developing the product, which was deployed on AWS. Data pipelining work integrated NoSQL & SQL vector databases with the enterprise data warehouse. AI/LLM techniques included reasoning/action (reAct) & retrieval augmented generation (RAG); in particular hierarchical RAG and contextual compression. Impact: The product increased user rating of resulting AI responses versus a naive GPT-4+RAG prototype by over 100%.See More

AI Automated Data Extraction

Developed a tool which works with PDF documents, uploaded or retrieved from a data warehouse, in AWS, to extract key fields relevant to the client's real estate information services. Used retrieval augmented generation (RAG), with the Chroma vector database, PGVector and GPT-4. Resulting data fields are pushed through a data pipeline to a QA app for human-in-the-loop processing.See More

Bibliograph: SaaS platform for transforming traditional library catalog formats into web linked data

Bibliograph AKA Library.Link Network, Acquired by EBSCO from the company I founded in 2020 My role: Conception of the idea, data and software architecture and design for the product, alongside co-founders, prototyping the idea and evolution through collaboration with a group of early-adopter libraries (starting with Denver Public Library). Leading from an engineering perspective the growth of the product into a commercial system which got acquired. The product used largely custom data pipelining using Python, with a PostgresQL database and a templating to write static web pages with embedded RDF structured metadata, including JSON-LD, with judiciously crafted dynamic components, in order to support our extraordinary scale—the output from 10 large library catalogs alone dwarfs all of Wikipedia, and there are thousands of such in the addressable market. Product is a SaaS platform running on AWS (being migrated to AWS post acquisition). The product has proven highly strategic in restoring libraries to public availability on the modern web, including a partnership with Google to use our web data feeds to drive borrow actions in Google Search knowledge panels.See More

Inclusive Guide: online reviews and community towards inclusion & social justice

My role: Engineering Leadership, as CTO, and support for ongoing funding efforts. This evolved from a startup business advisor to a hands-on, part-time, contract role in order to help launch the Inclusive Guide, an online community that lists and rates safe and welcoming spaces for anyone that faces discrimination. Individuals can rate businesses and spaces on their customer service experience relating to each person’s specific identities (race, ability, gender, etc).See More

10minclimate.com

Saving Nature's Wonders, 10 Minutes At a Time: AI-Personalized Approach to Climate News Developed an AI/LLM powered tool to deliver subscribers personalized news summaries and calls to action on climate topics. Goal is to make climate news less overwhelming and discouraging. Contributions I developed the idea and rapidly assembled a team of 9. I led software and data pipeline implementation applying open-source AI, Async.io, Python, Docker Compose, Machine Learning, and NLP techniques, while designed REST API integrations to ensure efficient process and data flow. I mentored team members and drove collaboration to ensure a smooth development process. Outcomes The project was a success, with the initial prototype being completed in a 20-hour sprint from conception, and winning 2nd place at the Boulder Startup Week hackathon. The tool was further honed for ClimateCon! helping attendees with accessible and actionable climate news, applying AI and personalized content to tackle global issues.See More

Work History

Vice President & Principal Architect

EBSCO Information ServicesMar 2020 - Mar 2023 • 3 yrs 1 moEngineering & architectural leadership in Bibliograph, a high-scale (dwarfing all of Wikipedia) SaaS platform for transforming library catalog formats into Linked/Knowledge Graph Data on the Web, and a wide variety of microservices & analytics over the resulting data.

Chief Technology Officer

ZepheiraJun 2007 - Mar 2020 • 12 yrs 10 mosPractice & engineering leadership in services helping organizations apply advanced data/web tech to organize, share and enhance information in hybrid automated/human-directed problem solving. Work with multiple clients to deliver solutions. Executive steering in strategy, marketing, sales, HR, etc. Small sampling of projects: Cisco Systems, Inc.—prototyped internal, globalized metadata management system; professional assessment on content strategy for Cisco sites (marketing and customer support) US Library of Congress—built ViewShare.org, large-scale collection management/visualization platform for digitized assets. Developed next-gen library records standard (bibframe.org) Online Computer Library Center (OCLC)—built public web identifier & x-referencing engine (purl.org). Strategized incorporation of Google Knowledge Graph into records management Lilly/Quintiles Transnational/Semio—prototyped an information platform/data warehouse to accelerate drugs development. Built a semi-structured Web health portal World Health Organization (WHO)—built a collaborative platform for the Health Information Standards initiative (ICD plus other data & statistics for Millennium Development Goals)

Practice Manager, Chief Technology Officer & Founder

Fourthought LLCFeb 1998 - Jun 2007 • 9 yrs 5 mosPractice & engineering leadership in enterprise software architecture solutions. Pioneered integration of web tech advancements with traditional business systems. Designed & implemented open source and commercial XML, Web Services, Semantic Web and Knowledge Graph applications Small sampling of projects: Sun Microsystems—Enterprise content management platform unifying product & marketing information company-wide. Semantic Tech integrated with RDBMS & Java middleware Phillips Petroleum—Application of geo-coded metadata to natural resources exploration G.E. Access—XML AssessmentSM process to assist in migration of EDI, ERP and order-entry client-server systems into enterprise data bus iWitness—Distributed data store for secure electronic transactions. Adapting CORBA with Oracle, XML messaging, declarative business rules management and LDAP enterprise directory

Education

Milwaukee School of Engineering

Bachelor's degree, Computer EngineeringSep 1991 - Feb 1994

University of Nigeria, Nsukka

3 Years of Study, ELectronic EngineeringSep 1986 - May 1989

How Pangea Works

Effortlessly discover top talent

We’ve distilled the candidate search from endless hours down to just a few minutes. Using Pangea’s AI-powered search tools, you can find top fractional talent able to take on your next project. Our system looks at your company’s niche and your needs to find the perfect match faster than any traditional hiring platform.

Start working with talent today

The top talent on Pangea is ready to get started with you right now. You can message or hire a candidate right from their profile page and start assigning work as soon as they respond. And the best part? Pangea’s fractional contract structure lets you start small and ramp up as your needs change, keeping your costs manageable and your team’s capabliities flexible.

Track work and invoices in one place

Assign tasks, track progress, and complete invoices all on Pangea. We’ve combined every part of the hiring process into one platform to eliminate the miscommunication that’s unavoidable on other freelance platforms. We even send out 1099s to your contractors at the end of the year!

Talk with a Talent Expert

Members of our team are available to help you speed through the hiring process.

Available Now

Book a Call