OPEN TO ML / AI ENGINEERING ROLES/ASSOCIATE PRODUCT ENGINEER @ MARKOPOLO AI/RAG · LLM AGENTS · MECHANISTIC INTERPRETABILITY/AIMING FOR A PHD IN EUROPE/

Machine Learning & AI Engineer

Dhaka, Bangladesh --:-- local

AHAMMAD NAFIZ

I build retrieval systems and LLM agents that hold up outside a notebook.

I'm an engineer on DeepDive at Markopolo AI, working across the TypeScript monorepo and the Python scraping and annotation pipeline under it. Before that I owned the eval service at AskTuring.ai, building the retrieval and benchmarks for a production RAG system. Most of my reading still goes to mechanistic interpretability.

Open to ML / AI roles & research collaborations

Now
Associate Product Engineer, Markopolo AI
Before
Jr. Software Engineer, AskTuring.ai
Focus
RAG · LLM Agents · Interpretability
Goal
PhD in Europe, then a frontier lab
( 01 )

About

I'm a data science student at UIU and an ML engineer. Right now I work on DeepDive at Markopolo AI. Before that, at AskTuring.ai, I owned the evaluation service and built Deepen Answer, a RAG pipeline that pairs extended-thinking models with an agent that fills its own knowledge gaps.

I tend to learn things by rebuilding them. An autograd engine in NumPy. A memory layer for agents that cuts the context you send by 17× without giving up accuracy. A research agent that plans, searches, and cites its sources. Lately I keep drifting toward interpretability, trying to work out what these models are actually doing inside.

Next I want a PhD in Europe, and after that a lab working on the frontier.

[ Experience ]

  • Markopolo AI

    Aug 2026 — Present

    Associate Product Engineer, DeepDive

    Building full-stack features for DeepDive, an AI social listening and narrative intelligence platform, across a TypeScript monorepo and the Python scraping and LLM annotation pipeline that feeds it.

  • AskTuring.ai

    Sep 2025 — May 2026

    Jr. Software Engineer (former)

    Owned the eval service and admin dashboard, automating RAG benchmarks over HotpotQA, MuSiQue, FinQA, and CUAD. Built Deepen Answer: extended-thinking LLMs, an agent that fills its own knowledge gaps, and hybrid BM25 + vector retrieval with RRF.

  • United International University

    Dec 2025 — Feb 2026

    Research Assistant

    Researched autonomous agents and multi-agent systems, and contributed to papers on LLM applications, retrieval, and agentic workflow design.

B.Sc. in Data Science — UIU

2023 — Present

[ Recognition ]

Oct 2025

Champion — IC6 University Innovation Hub

BDT 60,000 pre-seed after a 15-week program.

Jan 2025

Best Prototype — Blockchain Olympiad

Team Auctra, UIU CSE Fest. BDT 20,000 prize.

Jun 2024

Champion — CSE Project Show (Predicta)

End-to-end data analysis & ML platform.

2024

1st Runner-Up — Data Innovators Challenge

Sales analytics track.

( 02 )

Skills

Languages
PythonC++SQLBashCUDA
ML / DL
PyTorchscikit-learnXGBoostCatBoostNumPyPandasOpenCVMatplotlib
LLM & GenAI
LangChainLlamaIndexLangGraphHF TransformersCrewAIAutoGenvLLMOpenAI APIAnthropic API
Agent Stack
ReActTool UseFunction CallingMulti-AgentSupervisor / SwarmAgent MemoryLLM Evaluation
Retrieval
Retrieval-Augmented GenerationHybrid SearchBM25Vector SearchReciprocal Rank FusionGraph Traversal
Fine-tuning
LoRAQLoRAPEFTSFTRLHFInstruction Tuning
Inference
vLLMONNXTensorRTBentoMLTorchServeQuantization
Backend / MLOps
FastAPIDockerKubernetesMLflowW&BDVCGitHub Actions
Databases
PostgreSQLpgvectorMySQLChromaFAISSPineconeWeaviate

Domains — RAG · LLM Evaluation · AI Agents · NLP · Computer Vision · MLOps · Mechanistic Interpretability

( 03 )

Work

( 04 )

Contact

If you're hiring for ML or AI work, want to talk research, or just have a good problem worth nerding out over, my inbox is open.

ahammadnafiz86@gmail.com

© 2026 Ahammad Nafiz

Dhaka, Bangladesh

Portfolio / V5