Ratanlal Mahanta

Computational Finance | AI-Driven Quantitative Research

⚙️ Algorithmic Trading & Quantitative Research

🚀 What We Build

Statistical arbitrage strategies using Python & C++
Backtesting engines with high-resolution market data
Signal generation pipelines using machine learning
Real-time execution systems with low-latency gateways
Portfolio optimization under risk and liquidity constraints

📈 Tech Stack

Languages: Python, C++, R, Rust, Julia
Tools: NumPy, pandas, QuantLib, TensorFlow, PyTorch
Infra: NGINX, EC2, Docker, Kubernetes
Deployment: CI/CD pipelines, GitHub Actions, Terraform

🧠 Focus Areas

Mean Reversion & Momentum Strategies
Options Volatility Arbitrage
Machine Learning in Financial Forecasting
High-Frequency Execution Models
Risk Management & Model Validation (CVA, FRTB, IRRBB)

🛠️ Quant Dev & Engineering

Monte Carlo Simulation Engines for derivatives pricing
LSM-based Bermudan Swaption Pricing & Hedging
Copula-based Credit & Counterparty Risk Modeling
Market Risk Engines for Repo, FX, IR, and Equities
Interactive Dashboards with Streamlit & Plotly

🔍 Model Validation

Independent Model Validation for CVA, FRTB SA/IMA
Benchmarking against QuantLib, Bloomberg & internal models
Automated Backtesting & Stress Testing frameworks
Governance-ready Documentation & Audit Controls
End-to-end reproducible validator pipelines

⚡ Algo Trading Infrastructure & Development

Low-latency execution gateways (FIX/FAST, WebSocket, DMA)
Distributed backtesting clusters for high-frequency data
Event-driven architectures with Kafka & Redis
Cloud-native deployment (AWS, GCP, Kubernetes)
Automated monitoring with Prometheus & Grafana
CI/CD pipelines for live algo strategy rollout