Skip to content
Sheharyar Ishfaq, home
Open to a six-month internship from 15 February 2027

who is sheharyar?

I AI and the systems they on.

Hover an underlined word, or

Lead engineer at Mavera for two years, on an AI platform used by 120+ companies. Now in the final year of an MSc in Computer Science at Sorbonne, Paris.

Sheharyar Ishfaq in a hangar beside a Rafale prototype
2yLead engineerMavera, 2024 to 2026Paris, FranceMSc at Sorbonne

Software I led is used by teams at

In numbers

What each word is backed by

My one-line summary, read the way a language model reads it. Hover a word to see what it pays attention to.

“Sheharyar”

pulls on everything after it, the way a subject should.

  • Lead engineer at Mavera Two years, 120+ companies0.31
  • MSc at Sorbonne Final year, Paris0.22
  • First place, Mistral hackathon Team of five, October 20260.19
Weights are set by hand to tell the story. “Sheharyar” attends to agents 0.38, builds 0.34, infra 0.18.

Selected work

01

Mavera

Lead software engineer, 2024 to 2026

  • 120+ companies
  • Led the team
Read the case study: Mavera

When someone asks the Mave Agent about their market, the desktop app sends the question to a planning model, which picks tools exposed over MCP. Retrieval pulls passages from the client's documents and meetings, and the answer streams back with its sources. The whole path runs on Kubernetes, which I operated as the platform grew.

One question, traced from the app to the cluster. Servers that expose reports, meetings and video to the agent. Desktop app: The window the question is typed into. Planning model: Tool-calling agents on OpenAI and Anthropic models. MCP tools: Servers that expose reports, meetings and video to the agent. Retrieval: Passages from the client's documents and meetings. Streamed answer: Word by word, with sources. Kubernetes: Everything above runs here, on AWS.
02

Bina.ai

Mistral LLM × Law Hackathon, Paris, October 2026

First place, team of fiveSee the project: Bina.ai

Hosted by Mistral AI, sponsored by Stanford Law School, Legora, Hector AI, Jus Mundi and Sciences Po.

Bina turns French data-protection rulings into briefs for litigation funders. A funder can't act on a brief that misquotes the ruling, so the backend I built checks every quoted sentence, word for word, against the original, and keeps any it can't find out of the pitch.

Draft brief

The regulator found that “the company did not implement measures appropriate to the risk” and noted that “customers were never informed of the breach”.

Press the button to check both quotes.

Source ruling, page 14

… the restricted committee considers that the company did not implement measures appropriate to the risk, within the meaning of Article 32 of the GDPR. The customers concerned were informed by email on …

The quote check, on example text. Draft brief, checked against the source ruling, page 14: First quote found on page 14. Second quote isn't in the source, so it's flagged and kept out of the pitch.
03

AIWrappers

Client project, 2025

  • 38 models
  • Paying customers
Watch the demo: AIWrappers

Someone describes an AI tool in plain words. An agent builds it as a working web app on the customer's own domain, and every app runs on one platform that routes its requests to 38 models from five providers, on the owner's own keys.

One agent builds many apps; every request goes through one model router, on the owner's own keys. Creator agent builds app.client-one.com, tools.client-two.io, ai.client-three.com and more; every app sends its requests to 38 models, 5 providers, one router.

What people I've worked with say

He moves quickly, asks sharp questions, and has a strong ability to take early ideas or partial direction and turn them into well-structured, working systems.
Jill Axline, PhDCo-founder and CEO, Mavera
Sheharyar is the kind of person you can trust with the hard stuff. He's thoughtful, dependable, and quietly makes everyone around him better.
Bill HickmanFounder, Hybrid Minds; former Chief Growth Officer, Leo Burnett Worldwide
Read the full recommendations on LinkedIn

Everything I've built, on one map

Placed by what each project is about, the way an embedding model would. Each small dot is one of 165 freelance projects.

Lead engineer2024

Mavera

AI market-intelligence platform. I built it end to end, then led the developers who joined.

120+companies using it

  • Next.js
  • Rust
  • MCP
  • Kubernetes
Closest on the map
Read the case study: Mavera
Positions and scores are set by hand to show how the projects relate. 12 projects and 165 freelance dots, grouped into Agents and LLMs, Systems and research, Machine learning, Product engineering.

Now

Sorbonne Université, 2025 to 2027

This year I'm going below the agents: GPU programming in CUDA, parallel computing with MPI, and deep learning for vision. Last year I ranked first of seventeen in System Design and validated a Rust traceroute engine at the LIP6 lab.

render_name<<<7, 72>>>
A tiny CUDA kernel: 504 threads in 7 blocks, each lighting one dot. The lit dots spell SHEHARYAR.

Writing

Things I built, then explained.

All stories on Medium
Sheharyar Ishfaq at BIG, the Bpifrance gathering of entrepreneurs at the Accor Arena in Paris
At BIG by Bpifrance, Accor Arena, Paris.

I like knowing what happens under the button.

I started freelancing in the second year of my degree and shipped 165 projects for clients. Then came an operations platform for a restaurant group in Dubai, a document editor for researchers in Finland, and two years leading engineering at Mavera, all remotely, before I moved to Paris for my master's.

Based in
Paris
Languages
English, French (learning)
Strengths
LLM agents, retrieval, Rust, Kubernetes
Learning
CUDA, MPI, PyTorch
Available
From 15 February 2027
Paperwork
Convention de stage

Let's build something together.

Six-month internship in Paris from 15 February 2027. Sorbonne signs the convention de stage, so there's no visa paperwork on your side. I reply within a day.