AI & LLM Engineering
Building practical systems around LLMs, RAG, embeddings, AI agents, and model integrations.
Muhammad Sesay
Full Stack Developer & Software Engineer in Freetown, Sierra Leone — building web apps, backend systems, and AI tools.
I work across JavaScript, TypeScript, Python, and Go: React and Next.js on the frontend, APIs and PostgreSQL on the backend, plus LLMs, MCP, and AI agents. I write about what I learn along the way.
What I'm building
I'm a full-stack developer and software engineer in Freetown, Sierra Leone. I still ship web applications and backend systems, and I'm spending more time on AI-powered workflows, developer tools, and writing about what I learn.
Developer Tools
Exploring tools that help developers work with AI, including MCP and AI-assisted development.
Full-Stack Systems
Building production-oriented web applications with modern frontend, backend, and database technologies.
Learning & Writing
Documenting what I learn through technical articles and Law for Software Developers.
Featured projects
Recent work that best shows how I build — AI tooling, full-stack product, and systems I can talk about in public.
Developer Tools
DevAssist
An MCP server that exposes project listing, code search, and git summaries to AI clients such as Cursor.
- Python
- MCP
- Streamable HTTP
- Starlette
- Uvicorn
- Cursor
AI / LLM
LEPA Support Agent
A LangGraph support workflow for LEPA: typed state, conditional routing, tools, memory, and a multi-agent split behind FastAPI.
- Python
- LangGraph
- FastAPI
- SQLite
- OpenRouter
AI / LLM
AI Document Processing Pipeline
An async document pipeline: upload or webhook, Temporal extract/analyze/summarize, then Trigger.dev email — without blocking the request.
- Temporal
- Trigger.dev
- TypeScript
- Webhooks
- LLM
AI / LLM
AI Job Application Assistant
Parse a job and a CV, explain the match, draft materials, then stop for a human. The AI never applies.
- Python
- LangGraph
- FastAPI
- Human-in-the-loop
- Evaluation
Recent articles
I document what I learn while building — MCP, agents, tool calling, and software engineering.
Agentic AI Is a Workflow, Not a Smarter Prompt
From reflection and tool use to evals, planning, and multi-agent systems — the concepts that changed how I think about building AI applications.
I Built an AI Job Application Assistant
Parse a job and a CV, explain the match, draft materials, then stop for a human. The AI never applies.
I Built an AI Document Processing Pipeline
How I combined webhooks, Temporal workflows, AI summarization, async notifications, and email into one small system.
Experience
Recent roles, with the work itself rather than a résumé dump.
JoinHelix.co
Full Stack Developer · Remote
June 2026 – August 2026
Member platform and AI workflows around community calls, retrieval, and scheduled agents.
Recyclium AG
Full Stack Developer · Remote
September 2024 – September 2025
Product tracking, reporting, and operations tooling for a deposit-return style product workflow.
Legacy Network AG
Full Stack Developer · Remote
June 2023 – April 2024
Backend work around blockchain-backed client data, referrals, and cloud deployment.
Skills & technologies
Grouped by how I actually use them — not a proficiency chart.
Languages
- Go
- Python
- JavaScript
- TypeScript
Frontend
- React
- Next.js
- Redux
- HTML5
- CSS3
- Tailwind CSS
- jQuery
Backend
- Go
- Node.js
- REST APIs
- PostgreSQL
AI / LLM
- LLM integration
- Prompt engineering
- RAG
- Embeddings
- AI agents
- MCP
- Ollama
Infrastructure
- Docker
- Redis
- MinIO
- Render
- Vercel
- Git
- GitHub
Mobile
- React Native
- Expo
Let's talk
WhatsApp is fastest. Email works if you want a written trail.