Skip to content
Anna.Mosaki
Open to roles · US & Europe · Immediate start

Anna Mosaki

Quantitative Researcher · Data Scientist · AI Engineer

ENSAE-trained quantitative researcher with hands-on experience at BNP Paribas CIB. I build ML systems for markets — NLP, time series, and multi-agent AI — and ship them with clear methodology.

View projectsDownload CVContact
scikit-learnTensorFlowPyTorchNLPTime SeriesParis, France

Builds

Projects

Live demos and planned builds — open a demo or dig into the source.

01Live

LLM Foundations

Climb a 12-rung ladder from a memoryless prompt to GraphRAG, evals, agents, and MCP — each step queryable live.

Pythonpydantic-aiOpenAIGraphRAGMCP
Open demoSource
02Live

Agent Desk

Multi-agent investment desk over FastA2A — live graph of agent traffic with human approval gates.

pydantic-aiFastA2AMCPFastAPISSE
Open demoSource
03Live

Research Digest

Live ArXiv + fund/quant RSS digest on time series × finance — free sources, SSE regenerate.

ArXivRSSFastAPISSENext.js
Open demo
04Coming soon

Sentiment Bench

Financial NLP benchmark: FinBERT vs LSTM vs local LLM — accuracy, latency, and alpha.

PyTorchFinBERTLLMbacktest

What will be here

  • Accuracy, F1, calibration (ECE)
  • Latency and cost per 1k docs
  • Downstream long/short Sharpe comparison
05Coming soon

Forecast Bench

Time-series foundation models on returns and volatility — purged walk-forward.

TimesFMChronos-2Moiraistatsforecast

What will be here

  • Returns & vol targets (not price levels)
  • CRPS / MASE leaderboard
  • Contamination-aware evaluation windows

Highlights

Award

1st Place

GenAI Hackathon — AWS, Mistral, Sia Partners, Gide

RAG system to automate legal document completion.

Award

1st Place

H-W3B Hackathon — Sia Partners, Tezos

Blockchain-secured digital car passport in Solidity.

Award

Best Internship Prize

ENSAE Paris

Recognized for quantitative research internship impact.

CV

Experience

BNP Paribas CIB

Oct 2024 – Sep 2025

Quantitative Researcher – Data Scientist, GM Quantitative Research & Engineering (PnL)

Paris, France

  • Built anomaly-detection models on financial time series, improving signal quality and monitoring for front-office trading desks.
  • Partnered with quantitative and risk teams to translate model outputs into actionable risk-reduction recommendations.
  • Contributed to an NLP pipeline analyzing trader communications, supporting compliance and market-intelligence workflows.

BNP Paribas CIB

Jun 2024 – Sep 2024

Summer Intern, Quantitative Researcher – Data Scientist

Paris, France

  • Developed and evaluated deep learning models for cross-asset pattern detection; improved accuracy of internal risk dashboards.
  • Presented technical results to senior stakeholders through structured memos and executive-ready presentations.

Les Associations Mutuelles Le Conservateur

Jun 2023 – Aug 2023

ALM Modeling Intern

Paris, France

  • Quantified portfolio Vega sensitivities to inform asset allocation and asset-liability management strategy.
  • Built Excel and VBA tools to automate financial simulations for the investment team.

Selected academic projects

  • Hi!ckathon (Hi! Paris, VINCI, L'Oréal, Schneider Electric, Capgemini, TotalEnergies): groundwater-level forecasting model.
  • Greenwashing Detection (ENSAE): NLP + regression measuring impact of corporate communications on investor behavior.
  • Energy Demand Forecasting (ENSAE): national electricity consumption forecasting for energy planning.
  • Chat-Doc (ENSAE): RAG web app to extract insights from user-uploaded documents (Python, Chainlit).