Junior AI EngineerGenerative AI • RAG • AgentsCasablanca, Morocco

Building Production-Grade AI Systems

Generative AI • RAG Architectures • LLM Fine-Tuning • AI Agents

I design and develop AI systems that solve real-world problems—from retrieval-augmented generation to LLM fine-tuning and full-stack AI application development. My work spans generative AI, prompt engineering, and building production-ready AI solutions with modern frameworks.

View Projects

Fine-tuning accuracy

+20%

Domain-specific accuracy with QLoRA fine-tuned Mistral 7B

Retrieval latency

-15%

Hybrid search optimization with Pinecone and ChromaDB

AI projects

6

Production-ready AI applications deployed

Capability Map

End-to-end AI delivery

Retrieval-augmented generation architectures

Multimodal-AI RAG App

-15% latency

LLM fine-tuning with LoRA and QLoRA

Legal-FAQ-Assistant

+20% accuracy

AI-powered application development

See portfolio

Full-stack AI integration with React and FastAPI

See portfolio

LocationMorocco
AvailabilityOpen for junior AI roles & consulting

Liquid Glass 2.0

Proof-first Bento grid

Frosted glass cards with container-query intelligence, highlighting velocity, reliability, and measurable outputs.

Systems that tell the truth

Eval-driven delivery

Golden sets + adversarial synthetic tests. Blocking regressions and monitoring hallucination risk before release.

Fine-tuning accuracy

+20%

Domain-specific accuracy with QLoRA fine-tuned Mistral 7B

Click to view project →

Retrieval latency

-15%

Hybrid search optimization with Pinecone and ChromaDB

Click to view project →

AI projects

6

Production-ready AI applications deployed

Click to view project →

Full-stack experience

4+ years

MERN stack and AI-powered web applications

Latency-aware pipelines

Performance under budget

Prompt packing, cache tiering, and hybrid retrieval keep p95s low while maintaining factuality.

Hybrid searchAsync routingToken budgets
Guardrails & safety

Policies and observability

Structured output validation, safety classifiers, and per-route scorecards visible in dashboards.

Policy-based tool access
Structured outputs with JSON schemas
Cost ceilings per task

Evidence over claims

Projects with measurable impact

Glass cards highlight the problem, architecture, and measurable outcomes for each build.

SheetBrain-AI

Enterprise teams needed automated spreadsheet error detection and formula auditing with policy compliance checks.

Enterprise automationReal-time auditing

Engineered an AI-powered formula auditing tool using TypeScript and Google Apps Script. Designed real-time recommendation engines with policy compliance checks and intelligent formula insights. Created seamless integration between cloud spreadsheets and LLM APIs.

TypeScriptGoogle Apps ScriptLLM APIsGSuite Integration
View DemoSource CodeImpact: Automated error detection and formula auditing for enterprise spreadsheets with real-time recommendations.

Multimodal-AI RAG App

Organizations needed to query multi-format documents with fast retrieval and contextual reasoning across different file types.

-15% retrieval latencyMulti-format support

Developed full-stack RAG application with FastAPI and React.js. Implemented hybrid search pipeline using Pinecone and ChromaDB, reducing retrieval latency by 15% through optimized metadata filtering. Integrated Google Gemini API for contextual reasoning.

FastAPIReact.jsPineconeChromaDBGoogle GeminiPythonTypeScript
Source CodeImpact: -15% retrieval latency for multi-format document queries with hybrid search.

Babel-Fish-Assistant

Real-time voice translation systems lacked seamless integration of speech recognition, translation, and natural voice synthesis for cross-language communication.

Real-time translationVoice AI

Developed a production-ready real-time voice translator integrating Deepgram STT and ElevenLabs TTS with GPT-4o-mini for high-accuracy cross-language processing. Built full-stack application with Next.js 14 and Flask backend for low-latency audio streaming.

Deepgram STTGPT-4o-miniElevenLabs TTSNext.js 14FlaskPythonTypeScript
Source CodeImpact: Production-ready voice AI system enabling real-time multilingual communication with natural speech synthesis.

Multi-Agent-AI-System

Complex AI tasks required autonomous orchestration of multiple specialized agents with tool-based workflows and collaborative decision-making.

Autonomous agentsTask orchestration

Engineered a Multi-Agent AI System capable of autonomous task decomposition and execution using tool-based workflows and collaborative agent architectures. Implemented agent coordination patterns with TypeScript for reliable multi-step task completion.

TypeScriptMulti-Agent SystemsTool-Based WorkflowsAI OrchestrationLangChain
Source CodeImpact: Advanced agentic AI system for autonomous task execution with intelligent agent collaboration.

AI-Powered-Meeting-Assistant

Manual meeting note-taking consumed significant time while missing key action items and decisions requiring follow-up.

Meeting intelligenceActionable summaries

Built a modern meeting intelligence platform that transcribes live audio and generates actionable summaries using state-of-the-art NLP models. Implemented real-time speech-to-text processing with Python and Flask, reducing manual note-taking time.

PythonFlaskSpeech-to-TextNLPWhisper APIOpenAI
Source CodeImpact: Intelligent meeting transcription and summarization reducing manual documentation overhead.

Technical credibility

Stack, tools, and how they are used

Interactive honeycomb shows exactly how each technology is applied in production workflows. Click to see implementation.

Large Language Models

Gemini, LLaMA, Mistral - fine-tuning and inference

Legal-FAQ-Assistant

LLM Fine-Tuning

LoRA, QLoRA, PEFT for domain optimization

Legal-FAQ-Assistant

RAG Architectures

Hybrid search and semantic retrieval

Multimodal-AI RAG App

Vector Databases

Pinecone, ChromaDB, FAISS for embeddings

Multimodal-AI RAG App

FastAPI

Asynchronous AI inference pipelines

Multimodal-AI RAG App

React.js & Next.js

AI-powered full-stack applications

Babel-Fish-Assistant

Python

AI systems and backend development

AI-Powered-Meeting-Assistant

Docker & Kubernetes

Containerization and AI deployments

Legal-FAQ-Assistant

Prompt Engineering

Structured outputs and agentic workflows

Multi-Agent-AI-System

PostgreSQL

Database architecture and SQLAlchemy ORM

SheetBrain-AI

Experience

Roles, outcomes, and delivery

Vertical timeline with glass connectors and measurable achievements for each role.

Full Stack Developer

Freelance01/2021 — Present
  • Designed and developed dynamic web applications using the MERN stack (MongoDB, Express.js, React.js, Node.js).
  • Created modern, responsive user interfaces utilizing Tailwind CSS, Bootstrap, and Sass.
  • Developed and integrated secure REST APIs and managed authentication solutions like JWT and OAuth.
  • Managed database architectures and optimized query performance using Mongoose and PostgreSQL.
  • Deployed and maintained production applications on cloud platforms including Vercel, Netlify, and Heroku.
  • Optimized website performance and SEO (Core Web Vitals) to improve search rankings and user retention.
  • Conceived and maintained custom WordPress sites, including theme and plugin development.
  • Developed interactive frontend functionality with JavaScript and backend logic in PHP.
  • Integrated AI-powered features using LLM APIs (chatbots, document analysis, automation tools).
  • Designed backend services for AI inference and data processing.
React.jsReact NativeMongoDBExpress.jsNode.jsHTML5/CSS3JavaScript ES6+ReduxTailwind CSSBootstrapSassJWT/OAuthMongoosePostgreSQLGit/GitHubDockerJestPostmanHerokuAWSNetlifyWordPressPHPLLM APIsFastAPI

Education & Certifications

Academic background and training

Formal education, professional certifications, and specialized training programs.

Professional Certificate, AI Developer

IBM01/2025 — 01/2026
  • Completed an intensive 10-course program focusing on the Full Stack AI Development lifecycle.
  • Developed core competencies in Generative AI, Prompt Engineering, and building AI-powered applications.
  • Gained hands-on experience in Python for Data Science, FastAPI/Flask, and creating specialized AI chatbots.
FastAPIModel Fine-TuningPrompt EngineeringLarge Language Models (LLM)PythonQLoRARetrieval-Augmented Generation (RAG)PEFTGenerative AI

Certification by Simplon in France and UM6P, Full Stack Developer

YouCode School10/2019 — 06/2021
  • Completed rigorous project-based training in modern web technologies and software architecture.
  • Specialized in the MERN stack and professional agile development methodologies.
React.jsReact NativeMongoDBExpress.jsNode.jsAgile MethodologiesHTML5/CSS3JavaScript ES6+ReduxCSS FrameworksResponsive DesignAuthentication & AuthorizationAPI DesignMongooseData ModelingGitHub/GitLabGitNPM/YarnDockerJestPostmanDebugging ToolsHerokuAWSNetlify

Bachelor of Science, Physics & Chemistry

Faculté Polydisciplinaire, Safi - UM6P10/2015 — 08/2018
  • Completed foundational coursework in physical sciences and mathematical analysis.
PhysicsChemistryMechanicsMathematicsFrench

High School Diploma, Physics & Chemistry

Lycée Kachkat09/2014 — 06/2015
  • Focused on advanced mathematics, physical sciences, and chemical engineering foundations.
MathematicsPhysicsChemistry

Next step

Let's build your next AI solution

Open for AI engineering roles and freelance projects.

© 2026 Achraf LachgarCasablanca, Morocco
Languages:ArabicFull Professional ProficiencyFrenchLimited Working ProficiencyEnglishFull Professional Proficiency