← All work

01 / Recommendations & agent workflows

Blink

Nov 2025 — Jul 2026
AI Engineer · Remote

Making the right connections.

At Blink, I delivered recommendation features that helped connect attendees and surface relevant sessions. Alongside that work, I designed and evaluated a separate beta workflow for flight creation.

  • Python
  • FastAPI
  • PostgreSQL
  • pgvector
  • LangGraph

Product engineering

Recommendations, delivered

I delivered attendee matchmaking and session recommendations using PostgreSQL/pgvector and Python/FastAPI services. The work included automated tests, CI/CD, and staged deployments.

I worked with product, frontend, mobile, QA, and backend colleagues to bring the AI features into the product.

Beta · Feature-flagged

A flight-creation agent in beta

I designed and evaluated a feature-flagged LangGraph agent with five tools covering booking, attendee search, location lookup, and document parsing. This was a beta agent workflow.

A Docling and Gemini 2.5 Flash extraction workflow converted flight and hotel PDFs and images into structured data. The recommendation features above were delivered; this agent remained an evaluated beta.

Feasibility evaluation

Evaluating self-hosted inference

I evaluated Gemma 3 12B with Ollama on AWS EC2 G5 GPUs. I measured time to first token, throughput, latency, memory, and GPU utilization to assess self-hosting feasibility.

Next case studyMENT

Let’s talk

Have something
in mind?

I’m open to applied AI, LLM, NLP/search, and AI backend opportunities across EMEA.

Submitting sends these details to Ahmad by email. Privacy details.

Powered by public portfolio facts

Ahmad’s AI Twin AI

A little curious?
You’re in the right place.

I’m Ahmad’s AI assistant. Ask me about his work, the systems he’s built, or the thinking behind them.

Start with a question. Follow your curiosity.

AI can make mistakes. Messages go to Groq to generate answers; this site does not store your chat.