Aqif Ahmed — AI Engineer

aqif@portfolio: ~

$ whoami

aqif ahmed — ai engineer · lahore, pk · utc+5

$ cat about.txt

i build ai on top of pre-trained models. prompts, rag pipelines, agents that call tools. python for logic, vector dbs for memory, apis for hands and feet.

$ ls ./stack

llms/ prompting/ rag/ agents/ mcp/ python/ fastapi/ docker/ postgres/

$ ./status

● open to ai engineering roles

aqif@profile: ~

$ cd ~/now $ ./contact

$ cat now.txt

now

Where I am, and where I'm pointed.

status open to ai engineering roles

building invisiblesearch (live github search) · net zero (expense app)

learning roadmap.sh ai engineer path — llms → rag → agents → safety

next ship an ai project with real retrieval, end to end

$ ls -la ./projects

projects

The same fundamentals an AI product runs on: typed APIs, structured responses, caching, clean deploys.

./InvisibleSearch

live github search engine

A minimal search engine over all of GitHub, live. Queries proxy straight to the GitHub search index through a FastAPI backend — the same pattern an LLM app uses to call an external API and shape its response.

Mapped raw API responses into typed, paginated results with a debounced, keyboard-navigable type-ahead — structured outputs, not loose JSON.
Rate-limit aware by design: a 60s per-query cache, structured 429s with reset timestamps, and quota warnings surfaced in the UI.
Containerized with Docker Compose; pytest suite runs against a mocked GitHub client.

[python][fastapi][javascript][docker]

↗ live ↗ github

./NetZero

cross-platform expense app

A cross-platform app for tracking expenses offline. A clean exercise in state and structured data — the same discipline a retrieval layer or agent memory needs.

Every record persists in local storage with no connection required — offline-first by design.
Built around a central state layer and reusable components, with validation at the input boundary.

[react-native][expo][javascript]

↗ live

$ cat skills.txt

skills

[llms] pre-trained models · tokens / context / inference · model selection · closed vs open-source

[prompting] system prompts · structured output · function calling · zero-shot / few-shot / chain-of-thought

[rag] chunking · embeddings · semantic search · rag vs fine-tuning · langchain / llamaindex

[agents] tools & function calling · react prompting · multi-agent workflows · mcp servers / clients

[data] chroma · pinecone · faiss · qdrant · postgresql · local storage

[backend] python · fastapi · rest apis · docker compose · git · linux

[safety] prompt-injection defense · bias / fairness · adversarial testing · input / output constraints

$ cat education.txt

education

[degree] BS Software Engineering — University of Central Punjab (UCP), Lahore

[coursework] DSA · Software Construction & Design · OOP · Advanced Web Programming · Applied Machine Learning · Formal Methods

[focus] AI Engineer — applying pre-trained models via LLMs, RAG, and agents (roadmap.sh)

[languages] English (professional) · Urdu (native)

$ ./contact.sh

contact

Have a model worth putting to work? Let's talk.

[email] aqifarain@gmail.com → [x] @aqifahmed_ → [github] @aqifahmed → [linkedin] /in/aqifahmed → [resume] download pdf ↓