Murad Baghirli

Legal Sentence Boundary Detection for Azerbaijani: 76ms → 3ms with Triton FIL

Sat, 31 Jan 2026 00:00:00 +0000

Status: Complete · Nov 2025 – Jan 2026 · GitHub

TL;DR
#

I built a sentence boundary detector specialized for Azerbaijani legal text, not general-purpose prose. It is a random forest classifier that decides, for every candidate terminator character (., !, ?, ;, quotes, newlines…), whether a sentence actually ends there. Each candidate is described by a 19-character context window plus 9 engineered linguistic and punctuation features. The model reaches 0.958 F1 on boundary detection.

AzNEOBERT — Azerbaijani BERT from Scratch on 12B Tokens

Thu, 01 Jan 2026 00:00:00 +0000

Status: In training · Phase 1 active on 8× NVIDIA H200 · Component 2 of the AzBERT pipeline

TL;DR
#

I am training AzNEOBERT — an Azerbaijani encoder language model from scratch, based on the NeoBERT architecture. The model runs on 8× NVIDIA H200 GPUs via SLURM, trained on ~12.2B tokens of Azerbaijani text across 11 corpus collections. Infrastructure stack: DeepSpeed ZeRO-2, Flash Attention 3, and torch.compile, reaching 1.24M tokens/sec throughput. Loss dropped from 11.1 (random init) to 2.35 within the first 4,100 steps.

e-qanun.ai - AI-Powered Legal Search for Azerbaijani Law

Thu, 25 Sep 2025 00:00:00 +0000

Status: Live in production · 25,000 users · ~1,000 queries/day · NAIC

TL;DR
#

I built the ML search pipeline for Azerbaijan’s national AI legal search platform at NAIC (National AI Center), part of the country’s AI Strategy 2025–2028. The system serves 25k users and ~1k queries/day across 500k+ legal documents, returning ranked results in under 200ms end-to-end.

About Me

Wed, 01 Jan 2025 00:00:00 +0000

I’m an ML Engineer and an MSE student in Computer Science at Johns Hopkins University, where I’m also a Graduate Course Assistant for Artificial Intelligence (EN.601.464).

Before Hopkins, I spent nearly three years at Azerbaijan’s National Artificial Intelligence Center (AZBA). There I built E-QANUN.AI, the national legal search platform: 50M+ vectors across Elasticsearch and Vespa, serving 7K+ monthly active users and 50K+ queries per month. I worked across the whole stack, from training retrievers and re-rankers to designing the RAG pipeline and fine-tuning LLMs on H200 clusters.

Contact

Wed, 01 Jan 2025 00:00:00 +0000

Open to ML engineering roles, research collaborations, and interesting NLP/retrieval problems. Best way to reach me is email.

mbaghir1@jh.edu linkedin.com/in/muradbaghirli github.com/muradbaghirli

Experience

Wed, 01 Jan 2025 00:00:00 +0000

Graduate Course Assistant
#

Johns Hopkins University · Baltimore, MD, USA Sep 2026 – Present

Support 136 students in Artificial Intelligence (EN.601.464) through weekly office hours and grading.
Contribute to course design, including homework and project development.

Machine Learning Engineer
#

National Artificial Intelligence Center (AZBA) · Baku, Azerbaijan Jul 2025 – Aug 2026

Murad Baghirli

Legal Sentence Boundary Detection for Azerbaijani: 76ms → 3ms with Triton FIL

TL;DR #

AzNEOBERT — Azerbaijani BERT from Scratch on 12B Tokens

TL;DR #

e-qanun.ai - AI-Powered Legal Search for Azerbaijani Law

TL;DR #

About Me

Contact

Experience

Graduate Course Assistant #

Machine Learning Engineer #

TL;DR
#

TL;DR
#

TL;DR
#

Graduate Course Assistant
#

Machine Learning Engineer
#