AG
INT
RES
University of Miami '26

Building intelligent
systems that matter

Software engineer and ML researcher specializing in agentic AI, computer vision, and real-time systems. Currently exploring the intersection of healthcare and machine learning.

Startup acquired by UMiami
ML Research at RCSI Dublin
3
Majors
7+
Projects
1
Acquisition

Personal Projects

A comprehensive collection of 12 machine learning and 30 quantitative finance projects demonstrating end-to-end implementation from research to production.

Image Classification

Machine LearningComputer Vision

Deep learning image classification using CIFAR-10/ImageNet with ViT, EfficientNet, and ConvNeXt architectures.

PyTorchVision TransformerEfficientNetConvNeXt+3
Click to view details

Object Detection

Machine LearningComputer Vision

Real-time object detection with YOLOv8, DETR, and Detectron2 achieving 30+ FPS inference.

PyTorchYOLOv8DETRDetectron2+3
Click to view details

Instance Segmentation

Machine LearningComputer Vision

Pixel-level object segmentation using Mask R-CNN, SAM, and panoptic segmentation on Cityscapes.

PyTorchMask R-CNNYOLACT++Segment Anything (SAM)+2
Click to view details

Text Classification

Machine LearningNatural Language Processing

NLP sentiment analysis with BERT and RoBERTa fine-tuning achieving 95%+ accuracy on IMDb.

TransformersBERTRoBERTaHugging Face+3
Click to view details

Text Generation

Machine LearningNatural Language Processing

Language model fine-tuning with GPT-2 and LoRA achieving perplexity under 25 on WikiText.

TransformersGPT-2GPT-NeoLoRA/PEFT+2
Click to view details

Machine Translation

Machine LearningNatural Language Processing

Neural machine translation with MarianMT and M2M-100 for multilingual translation.

TransformersMarianMTmT5M2M-100+3
Click to view details

Speech Emotion Recognition

Machine LearningSpeech & Audio

Audio-based emotion classification with Wav2Vec2 achieving 87%+ accuracy on RAVDESS.

PyTorchWav2Vec2torchaudiolibrosa+2
Click to view details

Automatic Speech Recognition

Machine LearningSpeech & Audio

End-to-end ASR with Whisper and Wav2Vec2 achieving WER under 5% on LibriSpeech.

TransformersWhisperWav2Vec2torchaudio+2
Click to view details

Recommender System

Machine LearningRecommendation Systems

Neural collaborative filtering with GNN achieving RMSE under 0.82 on MovieLens.

PyTorchSurprisePyTorch GeometricRedis+2
Click to view details

Time Series Forecasting

Machine LearningTime Series

Multi-horizon forecasting with Temporal Fusion Transformer and N-BEATS on M4/ETT datasets.

PyTorchTFTN-BEATSProphet+2
Click to view details

Anomaly Detection

Machine LearningAnomaly Detection

Unsupervised anomaly detection with autoencoders and isolation forests for industrial IoT.

PyTorchscikit-learnIsolation ForestLSTM-AE+1
Click to view details

Multimodal Fusion

Machine LearningMultimodal Learning

Vision-audio-text fusion with cross-attention achieving 15-30% accuracy improvement.

PyTorchCLIPImageBindTransformers+2
Click to view details

Adaptive Market Making

HFT StrategiesMarket Making

C++ market making engine with Python RL agent for dynamic quote skewing and inventory management.

C++17PythonPyTorchpybind11+2
Click to view details

Order Book Imbalance Scalper

HFT StrategiesMarket Making

Sub-second trading on micro-alpha signals from order flow imbalance and queue depth analysis.

C++17PythonNumbaLock-free buffers+1
Click to view details

Queue Position Modeling

HFT StrategiesExecution

C++ queue position estimation with dynamic cancel/replace for top-of-book priority.

C++17Poisson ProcessSurvival Analysis
Click to view details

Cross-Exchange Arbitrage

HFT StrategiesArbitrage

Latency-aware multi-venue arbitrage accounting for fees, rebates, and cancel risk.

C++17Multi-threadingUDP/TCPFIX Protocol
Click to view details

Short-Horizon Trade Imbalance

HFT StrategiesAlpha Signals

Predict next N ticks using OFI, trade signs, and microprice with sub-millisecond signals.

C++17PythonNumbascikit-learn+1
Click to view details

Iceberg Detection & Sniper

HFT StrategiesExecution

Detect hidden liquidity via partial fills and refill patterns for optimal execution.

C++17Pattern RecognitionStatistical Analysis
Click to view details

Latency Arbitrage Simulator

HFT StrategiesSimulation

Educational simulator for studying stale quote exploitation with controllable jitter.

C++17PythonEvent SimulationStatistical Modeling
Click to view details

Smart Order Router (SOR)

HFT StrategiesExecution

Rebate-aware cost model minimizing impact, fees, and opportunity cost across venues.

C++17OptimizationMulti-venueFIX Protocol
Click to view details

RL Market Maker

HFT StrategiesMarket Making

PPO/DQN agents on C++ LOB environment with Gym-style interface via pybind11.

C++17PythonPyTorchpybind11+1
Click to view details

Factor Research Toolkit

Research & BacktestingFactor Investing

Cross-sectional equity/crypto factor research with point-in-time data handling and Alphalens validation.

PythonpandasAlphalensPyfolio+2
Click to view details

Event-Driven Backtester

Research & BacktestingBacktesting

Comprehensive backtesting framework with vectorized and event-driven engines and walk-forward CV.

PythonNumbaRedispandas+2
Click to view details

Statistical Arbitrage Framework

Research & BacktestingStatistical Arbitrage

Cointegration-based pair/cluster trading with Kalman filter hedge ratios and regime filtering.

Pythonstatsmodelspykalmanhmmlearn+2
Click to view details

Options Volatility Surface

Research & BacktestingOptions

Arbitrage-free vol surface construction with SVI/SABR calibration and Greeks computation.

PythonQuantLibpy_vollibscipy+2
Click to view details

Limit Order Book Simulator

Execution & InfrastructureSimulation

High-performance C++ LOB engine with Poisson/Hawkes arrivals and Python bindings.

C++17pybind11PythonMemory Pools+1
Click to view details

Execution Algorithms

Execution & InfrastructureExecution

VWAP, TWAP, POV, and IS algorithms with market impact modeling and TCA analytics.

PythonC++NumPycvxpy+1
Click to view details

Real-Time Feed Handler

Execution & InfrastructureInfrastructure

Low-latency C++ market data handler with lock-free structures and NUMA optimization.

C++17BoostTBBNUMA+2
Click to view details

Momentum / Trend-Following

Trading StrategiesMomentum

EMA/SMA crossovers, breakout detection, and multi-timeframe momentum strategies.

PythonpandasNumPyTA-Lib+1
Click to view details

Mean Reversion Strategy

Trading StrategiesMean Reversion

Z-score reversion, Bollinger Bands, and RSI-based mean reversion with pairs trading.

Pythonstatsmodelspandasscipy
Click to view details

Statistical Arbitrage

Trading StrategiesStatistical Arbitrage

Engle-Granger and Johansen cointegration with rolling hedge ratios for pairs/clusters.

Pythonstatsmodelsscikit-learnC++
Click to view details

Momentum vs Value Long-Short

Trading StrategiesFactor Strategy

Cross-sectional factor strategy with sector/market neutralization and risk-parity sizing.

Pythonpandasscipycvxpy
Click to view details

Options Strategy

Trading StrategiesOptions

Earnings straddles, systematic covered calls, and IV-RV spread trading.

Pythonpy_vollibpandasscipy
Click to view details

Execution & TCA

Trading StrategiesExecution

C++ execution algorithms (VWAP/TWAP/POV) with impact models and slippage analysis.

C++17Pythonpybind11pandas
Click to view details

Machine Learning Strategy

Trading StrategiesML Strategy

LSTM/Transformer forecasting with embargoed cross-validation and calibration.

PyTorchscikit-learnpandasOptuna
Click to view details

Regime Detection & Allocation

Trading StrategiesRegime

HMM/Markov-switching regime detection with dynamic momentum/mean-reversion allocation.

PythonhmmlearnstatsmodelsPyPortfolioOpt
Click to view details

Portfolio Construction & Risk

Trading StrategiesPortfolio

EWMA/Ledoit-Wolf covariance estimation with Kelly sizing and risk constraints.

Pythoncvxpyscikit-learnpandas
Click to view details

Advanced Regime Detection System

Trading StrategiesRegime Detection

Sophisticated HMM/Markov-switching regime detection with HDBSCAN clustering and meta-policy allocation.

Pythonhmmlearnstatsmodelsarch+4
Click to view details

LSTM/Transformer Forecasting System

Trading StrategiesML Forecasting

Advanced time series forecasting with embargoed cross-validation, calibration, and Kelly sizing.

PyTorchTransformersscikit-learnOptuna+2
Click to view details

Gym LOB RL Market Maker

Trading StrategiesRL Trading

OpenAI Gym limit order book environment with DQN/PPO/SAC agents for market making.

PythonPyTorchOpenAI GymStable-Baselines3+2
Click to view details

Hawkes Process LOB Engine

Execution & InfrastructureSimulation

C++ discrete-event LOB simulator with Hawkes process arrivals and Python bindings.

C++17pybind11PythonEigen+2
Click to view details

Ultra-Low Latency Feed Handler

Execution & InfrastructureInfrastructure

C++ market data feed handler with lock-free queues, FIX encoding, and p50/p99 latency tracking.

C++17Boost.AsioLock-freeNUMA+3
Click to view details
12
ML Projects
9
HFT Projects
4
Research
3
Execution
9
Strategies
42 total projects across 107+ technologies

Get In Touch

Interested in collaborating, have a job opportunity, or just want to say hello? I'd love to hear from you.

Or reach out directly via email

anishguntreddi@gmail.com