Skip to content
View UffaModey's full-sized avatar

Block or report UffaModey

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
UffaModey/README.md
Fafa Modey (@UffaModey) — Platform Engineer, Agentic AI Engineer, Python Software Engineer, Data Engineer Typing SVG

🛠️ What I Do

  • Agentic AI Engineering — RAG pipelines (LangChain, vector search, hybrid retrieval + reranking), structured LLM output with schema validation and retry-on-failure, confidence-based grounding/hallucination filtering, content-safety guardrails, and agentic automation (custom Claude Code agents, MCP tooling, LLM-driven PR review and issue triage).
  • Platform Engineering — Infrastructure-as-code with Terraform across multi-environment deployments, containerized services on Docker/Kubernetes/Azure Container Apps, event-driven workers (Azure Functions, Service Bus, Celery), CI/CD (GitHub Actions, Bitbucket Pipelines), and OpenTelemetry-based observability.
  • Python Software Engineering — Async-first APIs with FastAPI and Django/DRF, strict typing (mypy), SQLAlchemy + Alembic migrations, test-driven backend design.
  • AI Engineering — LLM integration across OpenAI, Azure OpenAI, and Claude; embeddings and vector search (Azure AI Search, MongoDB Atlas $vectorSearch, FAISS); token usage and cost accounting.
  • Data Engineering — Relational + NoSQL data modeling (Postgres, MySQL, Cosmos DB, MongoDB), message-queue-driven ingestion pipelines, ETL for document/knowledge stores feeding retrieval systems.

🌱 Currently

  • Building Tokenria — a local tool that breaks down LLM token spend by structural category (cache, tools, history, output) and separately tracks how much of what a model generates actually gets used, tagged by hand rather than auto-scored.
  • Deepening production RAG patterns: retrieval grounding, hallucination confidence-filtering, and guardrail testing for LLM-backed platforms.
  • Growing a Claude Code / MCP-based agentic tooling practice — custom agents for PR review, technical-debt triage, and dev workflow automation.

🧠 Skills

Python FastAPI · Django · AsyncIO
Cloud Platforms Azure · AWS · Azure OpenAI
Docker & Containerization
Kubernetes & Container Orchestration
Git, CI/CD & DevOps GitHub Actions · Azure DevOps · GitLab CI
SQL, NoSQL & Databases PostgreSQL · MySQL · Redis · Cosmos DB · Vector Databases
Infrastructure as Code Terraform
AI & LLM Frameworks LangChain · OpenAI SDKs · Azure OpenAI
Agentic AI MCP · Tool Calling · RAG · LLM-driven automation
API & Distributed Systems REST APIs · GraphQL · Message Queues · Event-Driven Architecture

📫 Get in Touch

LinkedIn X

Open to collaborating on agentic AI systems, RAG infrastructure, and platform engineering for AI-native products.

Pinned Loading

  1. tokenria tokenria Public

    See where your LLM tokens actually go, and how much of what you generate is actually worth using.

    Python

  2. civic-shield-mcp civic-shield-mcp Public

    An AI-powered Digital Rights Risk Analyzer for Activists

    Python

  3. advent_of_ai advent_of_ai Public

    An collection of AI engineering challenges completed as part of Goose’s Advent of AI.

    JavaScript 1

  4. document-analysis-api document-analysis-api Public

    AI Document Analysis API with AWS Textract and AWS App Runner

    PowerShell

  5. gratitude-journal gratitude-journal Public

    A full stack Figma to Code project for AWS Amplify and AWS Cognito

    JavaScript 1

  6. pictures2stories pictures2stories Public

    Transforming Images into Short Stories with AI and Azure Services

    Python