Fatemeh Rahimi

Senior NLP & AI Scientist

Fatemeh Rahimi

7+ years shipping production NLP and AI systems — from transformer fine-tuning and RAG pipelines to multi-agent LLM orchestration and document understanding. Currently leading AI development as a Senior NLP Scientist at Pythonic AI.

Featured Projects

Production and research highlights

Multi-agent Support Automation

Pythonic AI · 2023 – present

Designed and built an LLM-powered multi-agent system that autonomously triages and resolves support emails involving routine code and configuration changes. Uses prompt-engineered reasoning chains, tool orchestration, and human-in-the-loop escalation to reduce manual engineering effort.

PythonLLM APIsMulti-agent orchestrationRAGPrompt engineering

Production NLP Services

Pythonic AI · 2022 – present

Led end-to-end development and deployment of 3 production NLP services for document understanding. Primary technical owner for one service. Built evaluation pipelines to measure model quality and business impact across releases.

PythonPyTorchTransformersDockerREST APIsMLflow

Biomedical NLP Research

Imagia · 2020 – 2022

Researched and built NLP pipelines for clinical report analysis — including de-identification, named entity recognition, and measurement extraction. Applied transformer-based models (BioBERT, ClinicalBERT) to real-world hospital data.

PythonPyTorchspaCyBioBERTHugging FaceCLI tooling

MTLV: Multi-task Learning Library

Dalhousie University · 2020 – 2021

CLI library for exploring four multi-task learning architectures with pre-trained language models. Proposed a novel task-clustering approach that improved cross-task transfer. Published at ACM DocEng-2021; served as M.Sc. thesis.

PythonPyTorchBERTBioBERTBlueBERTHugging Face

Open Source

Contributions to public projects

Added four new tools to this MCP server for Microsoft 365 — create, create child, rename, and delete mail folders via the Microsoft Graph API. Closes a workflow gap where users couldn't set up destination folders before moving messages.

TypeScriptMicrosoft Graph APIMCPMail.ReadWrite

Work Experience

7+ years in NLP, AI, and production ML

Senior NLP Scientist

Feb 2022 – Present

Pythonic AI · Milwaukee, WI, US (Remote)

  • Led end-to-end development and deployment of 3 production NLP services for document understanding; primary technical owner for one
  • Architected a multi-agent LLM system with prompt-engineered reasoning, tool orchestration, and human-in-the-loop escalation to automate support email triage and resolution
  • Built RAG pipelines and evaluation harnesses to measure model quality, enabling data-driven iteration across releases
  • Developed automation tooling to streamline team workflows across data labeling, sprint planning, and QA
  • Coordinated cross-functional annotation pipelines and mentored team members on NLP best practices

Applied Research Scientist – NLP

Nov 2020 – Jan 2022

Imagia · Montreal, Canada (Remote)

  • Built NLP pipelines for hospital clinical report analysis — de-identification, named entity recognition, and measurement extraction
  • Applied and evaluated transformer-based models (BioBERT, ClinicalBERT) on real-world biomedical datasets
  • Designed production-grade CLI tools for end-to-end model inference on clinical documents

NLP Research Assistant

Mar 2019 – Apr 2021

Dalhousie University · Halifax, Canada

  • Applied and evaluated deep language models (BERT, BioBERT, BlueBERT) on downstream NLP tasks with rigorous experimental design
  • Developed MTLV — a multi-task learning library with 4 architectures and a novel task-clustering method (published at ACM DocEng-2021)

Data Analyst

Aug 2018 – Feb 2019

Ayten Company · Shiraz, Iran

  • Worked on social network analysis using Python, Neo4j, and MongoDB
  • Practised Scrum within an R&D software team

Skills

Core technologies and competencies

Languages

PythonSQL

LLMs & GenAI

Hugging Face TransformersRAG pipelinesLangChain / LangGraphOpenAI APIAnthropic APIMulti-agent orchestrationPrompt engineeringLLM evaluation

ML / DL

PyTorchscikit-learnMLflowModel fine-tuning (PEFT / LoRA)

NLP

spaCyNLTKBERT / RoBERTa / ELECTRADocument understandingNamed entity recognitionText classification

Data & Experimentation

NumPypandasJupyterA/B testingStatistical analysis

Infrastructure

GitDockerREST APIsMySQLtmux

Publications

Peer-reviewed research

MTLV: A Library for Building Multi-task Learning Architectures for NLP

Rahimi, F., Milios, E., Matwin, S.

DocEng 2021 — ACM Symposium on Document Engineering · 2021

Education

Academic background

M.Sc. Computer Science

Dalhousie University · Halifax, Canada

GPA 4.07/4.3 · Thesis: MTLV multi-task learning library

May 2019 – April 2021

B.Sc. Software Engineering

Shiraz University · Shiraz, Iran

Senior project: Kitchen Safety IoT system

Sep 2013 – Feb 2018

Contact

Get in touch

© 2026 Fatemeh Rahimi