Available for selected AI engineering projects — UTC+1

AI systems that
do real work.

RAG · AI Agents · Workflow Automation · Evaluation

I help teams automate knowledge-heavy and operational workflows — research, documentation, diagnostics, reporting — with AI systems built for real-world operation.

Evaluation, observability, failure handling, and deployment are considered from the beginning — not added after the demo.

Industrial AI Copilot,
30-case eval suite
90%
Answer accuracy
100%
Retrieval precision
3.09s
Avg. latency

What can AI take off your team's plate?

I build systems around workflows where teams spend too much time searching, researching, analyzing, classifying, reporting, or moving information between tools.

Knowledge & RAG Systems

Turn internal documents, technical knowledge, SOPs, and research material into AI systems your team can actually use.

Internal documentation, SOPs, technical manuals, policies, research libraries.

Intelligent Workflow Automation

Automate repetitive research, classification, monitoring, reporting, and decision-support workflows.

Research, reporting, classification, monitoring, and information processing.

AI Agents & Decision Workflows

Connect AI models to tools, data, and business processes to execute structured multi-step work.

Multi-step workflows that require reasoning, tool use, and structured decisions.

AI Evaluation & Reliability

Measure AI quality continuously and catch regressions before they reach users.

Teams already running AI systems that need measurable quality and regression protection.

Before we build anything

AI Workflow Assessment

I'll help determine whether AI is actually a good fit for your workflow — and what I would build if it is. Not every problem needs an agent; some need a script, and some don't need AI at all.

Is the workflow actually suitable for AI?
What data is available to work with?
What should stay deterministic, not AI?
Where can the system fail, and how loudly?
What level of human oversight is needed?
What would success be measured against?

I approach AI systems as engineering systems — not experiments.

My foundation in Mechanical Engineering trained me to think in terms of constraints, failure modes, tradeoffs, and system behavior. I brought that mindset into AI engineering: I design systems with real-world operation in mind — measurable evaluation, failure handling, observability, and reproducible deployment, considered from the start.

Each system in my portfolio started with a concrete workflow problem, not a technology I wanted to try. That means I can walk through why a given architecture was chosen, where it would break, and what changes under a different constraint — the kind of scrutiny a serious technical buyer or hiring manager should apply.

I'm available for AI engineering projects, contract work, and remote roles — with teams and founders who want someone who can own a system end-to-end, from diagnosing the workflow through architecture, deployment, and evaluation.

LangGraph CrewAI Hybrid RAG ChromaDB BM25 MCP FastAPI Docker AWS ECS Fargate CI/CD (OIDC) Gemini Vision Groq / Llama Cohere Rerank LLM-as-Judge HuggingFace LangSmith SQLite / JSONL
Location
Nigeria, UTC+1 — available remote or on-site
Education
B.Eng Mechanical Engineering
University of Uyo
Certifications
IBM RAG & Agentic AI Professional Certificate
Microsoft AI & ML Engineering Professional Certificate
Availability
Available for projects

Proof through working systems.

Each system started with a concrete problem, an architectural constraint, and a measurable definition of success.

Flagship

Industrial AI Copilot

AI-assisted industrial knowledge and fault diagnosis

Problem

Industrial troubleshooting can require searching technical documentation, interpreting equipment information, and combining multiple sources of evidence.

System

Built a multi-agent diagnostic system combining hybrid retrieval, specialist agents, live telemetry, image analysis, and tool integration.

Engineering challenge

Domain-specific terminology made pure semantic retrieval insufficient, leading to a hybrid dense + BM25 retrieval strategy with reranking.

Deployment

Migrated from Hugging Face Spaces to AWS: containerized on ECS Fargate behind an Application Load Balancer, with S3-backed vector store persistence and a GitHub Actions CI/CD pipeline authenticated via OIDC — no long-lived AWS credentials stored in CI.

Measured evidence

30-case eval suite · 90% answer accuracy · 100% retrieval precision · 3.09s average latency

LangGraph Gemini 2.5 Flash Hybrid RAG ChromaDB + BM25 Cohere Rerank MCP MQTT FastAPI Docker AWS ECS Fargate ECR S3 GitHub Actions / OIDC
Commercial fit

Busiv

Autonomous business intelligence workflow

Problem

Monitoring industry news and producing structured intelligence can consume hours of manual research every week.

System

Collect → filter → classify → deduplicate → synthesize → deliver. An autonomous pipeline that produces scheduled intelligence briefings — no human trigger required after deployment.

Engineering challenge

Raw news volume is mostly noise. A relevance-scoring and four-category signal layer (Regulatory, Product, Market, Hiring) filters what reaches synthesis, with a priority path for time-sensitive regulatory signals.

LangGraph APScheduler ChromaDB feedparser SendGrid FastAPI Docker

AgentEval

AI quality and regression infrastructure

Problem

AI systems can silently degrade as prompts, models, retrieval strategies, or orchestration logic change.

System

Built an evaluation framework for RAG, single-agent, and multi-agent workflows with LLM-as-judge scoring and CI/CD regression gates.

Business relevance

Provides a repeatable quality signal before changes are deployed.

Groq Llama 4 Scout LLM-as-Judge SQLite GitHub Actions FastAPI Docker

LexAI

AI-assisted contract intelligence prototype

Problem

Contract review involves extracting clauses, identifying risk patterns, and presenting complex language in a structured form.

System

Built a multi-agent document analysis pipeline (Senior Analyst → Legal Researcher → Risk Assessor → Plain Language Specialist) with structured risk extraction and domain-grounded retrieval against Common Law and UNIDROIT reference material.

Research prototype — not legal advice.

CrewAI ChromaDB LLM-as-Judge pdfplumber LangSmith FastAPI Docker

Not ready to talk yet? Read the flagship case study and see the architecture behind the numbers.

See the Case Study →

From fragmented documentation to an AI-assisted diagnostic workflow.

Industrial troubleshooting means searching manuals, reading equipment telemetry, and interpreting visual evidence — usually across three separate tools. The Industrial AI Copilot does this in one conversation.

Why not a basic chatbot

Domain-specific terminology made pure semantic retrieval insufficient. Combining dense vector search with BM25 keyword matching, then reranking, closed the gap between what the model retrieved and what a technician actually needed.

Limitations

Vision analysis depends on image quality from the field; telemetry integration currently assumes MQTT-compatible sensors. Both are documented, not hidden, in the source repository.

Where this generalizes

The same pattern — hybrid retrieval + live data + specialist agents + evaluation — applies to any operational workflow combining documentation, sensor data, and visual evidence.

From demo to production

Originally deployed on Hugging Face Spaces, later migrated to AWS — ECS Fargate, ECR, an Application Load Balancer, S3-backed persistence, and a GitHub Actions pipeline authenticated via OIDC rather than stored credentials. The migration surfaced a real production lesson: an ALB health check race condition, fixed by separating liveness from readiness so the service only reports healthy once retrieval and agents are actually loaded.

90%
Answer accuracy
100%
Retrieval precision
3.09s
Avg. latency
30
Evaluation cases

How I build AI systems.

A mechanical engineering foundation means I think about systems the way systems actually behave — with edge cases, failure modes, and constraints that matter in the real world.

Start with the constraint

Architecture follows the constraint, not the other way around.

Cost, latency, data quality, reliability, and workflow complexity determine architecture. I start there and work backward, which usually saves weeks of rebuilding.

Choose the simplest architecture

Use a single chain when a single chain is enough.

Introduce agents only when they provide a real capability advantage. Reaching for multi-agent orchestration by default is a tell of inexperience, not sophistication.

Evaluate before trusting

A system that hasn't been measured hasn't been proven to work.

I define measurable quality criteria and regression tests before assuming the system works — not after users start noticing problems.

Design for operation

Deployment is part of the system, not cleanup work.

Containerization, observability, failure handling, versioning, and reproducible deployment are considered from the start, not bolted on before a demo. The flagship system runs on AWS ECS Fargate with an automated, OIDC-authenticated CI/CD pipeline — not just a hosted demo link.

Where I can create leverage.

Founders building AI products

You have a validated problem and need someone who can turn the workflow into a reliable, production-grade AI system.

Teams drowning in information

Your people spend hours searching documents, researching markets, preparing reports, or processing information manually.

Companies with an AI prototype

You've built something that works in a demo but need better retrieval, evaluation, orchestration, or deployment to trust it in production.

Have an AI workflow worth automating?

Tell me what your team currently does manually, where the bottleneck is, and what you've already tried. I'll help determine whether AI is actually a good fit — and what I would build if it is.

Based Abuja, Nigeria — UTC+1