Muhammad S.

Key Skills

Software

AWS SageMaker

Appen

Argilla

Axiom AI

Clickworker

CrowdFlower

Dataloop

Datatroniq

Datumbox

Dataturk

Doccano

Google Cloud Vertex AI

HiveMind

V7 Labs

Internal/Proprietary Tooling

Top Subject Matter

Human Resources (HR) support chatbot and policy-compliant knowledge answering

Production RAG chatbots with multimodal document ingestion and retrieval pipelines

Legal Services & Contract Review

Top Data Types

Computer Code Programming

Image

Text

Document

Top Task Types

Action Recognition

Classification

Computer Programming/Coding

Data Collection

Fine-tuning

Prompt + Response Writing (SFT)

Function Calling

Freelancer Overview

I'm Muhammad Sohail, a Data & AI Engineer working at the intersection of applied research and production engineering. My focus is making large language models useful and reliable for real organizations — not just impressive in a demo. Originally from Pakistan, I now live and work in Paris, where I hold an M.Sc. in Data Science & Network Intelligence from Télécom SudParis at Institut Polytechnique de Paris. I currently work as a Data & AI Engineer at Université d'Évry Paris-Saclay, where I lead the design and deployment of the institution's internal AI platform. My work spans the full stack of modern AI engineering: retrieval-augmented generation, LLM serving and orchestration, containerized deployment, observability, and the careful integration work that turns raw models into tools people actually want to use. I care about the parts most demos skip — auth, monitoring, multilingual UX, latency budgets, graceful failure. Outside the office I'm a curious reader, an occasional cook, and I'm slowly learning French. I'm always open to interesting collaborations, freelance work, and conversations about AI systems that need to actually work.

Labeling Experience

Data & AI Engineer — Production RAG chatbot and multimodal document processing (Sep 2025 – Present)

DocumentFunction Calling

Designed and deployed production RAG-based chatbots to improve knowledge access across university HR and IT departments. Built end-to-end multimodal document processing pipelines (PDFs, images, and tables) with high content extraction accuracy to feed retrieval and answering components. Implemented retrieval optimization through reranking and hybrid search using vector stores to improve precision of the retrieved context. • Built multimodal document processing pipelines for knowledge extraction • Implemented FAISS/PostgreSQL hybrid search and reranking for retrieval precision • Integrated OpenWebUI with university systems and enabled tool calling flows • Set up monitoring and observability for production AI services using OpenTelemetry and Grafana

2025 - Present

Data Science Intern — Intelligent HR chatbot with LLM + RAG automation (Mar 2025 – Jun 2025)

DocumentPrompt + Response Writing (SFT)

Developed an intelligent HR chatbot using LLMs with Retrieval-Augmented Generation to answer recruitment, leave, and training inquiries. Built validation mechanisms intended to ensure responses are accurate and compliant with internal policies. The work involved preparing and utilizing document-derived knowledge for the chatbot’s retrieval and response generation pipeline. • Designed RAG flows for staff inquiry automation and contextual answering • Implemented response validation to reduce incorrect or non-compliant outputs • Created UI workflows using Streamlit and Gradio for interaction with the chatbot • Used document parsing tools (Unstructured.io, Docling, LlamaParse, pdfplumber) and LangChain to extract knowledge

2025 - 2025

Education

Work History