AnjolaAdeuyi

Senior Full-Stack + AI Engineer, Building production AI systems for Fortune 500 clients. I ship platforms that process millions of transactions daily.

View Work hello@anjolaadeuyi.com

Based in Paris

Open to remote work

AI Systems + FullStack

RAG, agents, benchmarks

Currently available

Starting

8+ Years Experience

Systems Architect

50+ engineers served

Selected Work

View all

LLMs.txt Generator

An intelligent web reader that normalizes, validates and streams text from any URL, optimized for LLM ingestion

View

UI component library

A collection of reusable UI components built with Tailwind CSS and React, designed to enhance the developer experience and improve code quality.

View

Agent Orchestrator

Multi‑tool planning, retries, guardrails, tracing via OpenTelemetry.

View

Clients

I've worked on products for the following clients and more

Safran

Huawei

Elastic

Andela

GitStart

Andera AI

Aitenders

Jenni AI

First Resonance

Novu

Rebill

Whop

PostHog

Appsmith

Parabol

Goodcall

Instrumental

Lightdash

ToolJet

MakeYourStats

Workflow

Qwik

Chakra UI

Material UI

Block Protocol

Budibase

Lens

Filecoin Saturn

PlugLink

Zaui

Mergestat

Hash AI

Hive

Flanksource

Wave

Skills & Technologies

With new tech comes new challenges; I welcome them. Here's a comprehensive overview of the technologies and tools I work with.

Frontend & UI

ReactNext.jsTypeScriptJavaScriptTailwind CSSHTML5CSS3SassFramer MotionGSAPThree.jsWebpack

Backend & Languages

Node.jsExpressPythonJavaGoGraphQLPrismaFastAPI

Databases

MongoDBPostgreSQLRedisSupabase

AI & ML

LangChainOpenAIAnthropic ClaudeRAGVector DatabasesLLM Fine-tuningvLLMOllamaPineconeVercel AI SDKLlamaIndex

DevOps & Cloud

DockerKubernetesAWSGoogle CloudVercelNetlifyGitLinux

Tools & Testing

FigmaESLintPrettierJestCypressStorybookPuppeteer

RAG Pipeline

~42 lines

from fastapi import FastAPI
from rag import embed, search, rerank, answer
from tracers import trace

app = FastAPI()

@app.post("/ask")
@trace("ask")
def ask(q: str, user_id: str):
    q_vec = embed(q)
    chunks = search(q_vec, k=20, filters={"user": user_id})
    ranked = rerank(q, chunks)[:6]
    return answer(q, ranked, tools=["browser", "code"], guardrails=True)

Timeline

2025
Software Engineer - Safran, France
Building neural network visualization platform serving 50+ aerospace engineers. Architected interactive tools using Electron.js, React, and D3.js.
2021 — 2025
Tech Lead — GitStart YC S19, USA
Led team of 6 engineers for 100k+ user platform. Built AI-powered compliance automation for Fortune 500 clients, achieving $300k annual savings.
2024 — 2024
AI Engineer - Aitenders, France
2019 — 2021
Team Lead — PlugLink
2019 — 2020
Software Engineer — Andela
2018 — 2019
DevOp Engineer — Huawei

Model Evals

Continuous evaluation of prompts, tools, and retrieval quality across production workloads.

Pass@1 by model (weekly)

Live data

Current best

82%

+4% this week

Context win

+10% RAG

vs baseline

Latency p95

780ms

Within SLA

Eval Categories

Code generation87%

Q&A retrieval82%

Tool usage76%

Reasoning73%

Recent Tests

GPT-4o prompt optimization

2 hours ago

Claude-3.5 tool calling

6 hours ago

RAG chunk size A/B test

12 hours ago

Evaluation Framework

1,247 total tests

Automated testing pipeline with custom metrics, human feedback loops, and A/B testing. Tracks accuracy, hallucination rates, tool usage effectiveness, and user satisfaction scores across different model versions and prompt templates.

About

I build AI products end‑to‑end: data ingestion, retrieval, prompt/tooling, evals, and production UI. Pragmatic about latency, cost, and safety — with strong attention to developer experience.

Years

120+

Projects

50+

Clients

Currently learning

Structured outputs, memory architectures and low‑latency tool use with vLLM + GPU batching.

Let's collaborate

Build with AJ.

hello@anjolaadeuyi.com

Schedule

Book a call

Social