Kuljeet Singh

CEO

Delhi, India2 yrs 6 mos experience

Most Likely To Switch

Key Highlights

Expert in designing data-driven trading algorithms.
Proven track record in quantitative finance and market making.
Strong background in machine learning and statistical modeling.

Stackforce AI infers this person is a Fintech expert specializing in quantitative research and algorithmic trading.

Contact

kuljeet.aech@gmail.com LinkedIn

Skills

Core Skills

Quantitative ResearchFinancial ModelingAlgorithmic TradingMachine LearningData Science

Other Skills

ATM straddlesAnalytical SkillsAutoencodersBacktestingComputer ScienceComputer VisionContextual BanditsCryptocurrency Market MakingData ModelingData VisualizationDeep LearningDelta/Vega hedging algorithmsFeature EngineeringHedgingHigh-Frequency Trading

About

Quantitative Researcher with a background in statistics, stochastic processes, and applied machine learning. I’ve built and deployed FnO strategies, mid-frequency models, and market-making systems across both traditional and crypto markets. Core competencies include Reinforcement Learning, Market Making, and Market Microstructures. My work focuses on designing scalable, data-driven trading algorithms that combine statistical rigor with real-time market dynamics.

Experience

2 yrs 6 mos

Total Experience

1 yr 5 mos

Average Tenure

2 yrs 6 mos

Current Experience

Bitqcode capital

Quantitative Researcher

Dec 2024 – May 2025 · 5 mos · Bengaluru, Karnataka, India

Achieved optimal behaviours for live strategies trading on Crypto (Spot and Perp Futures), TradFi (FnO and Equities), Gold and Commodities. Result, increased risk adjusted returns with average increase of 24%.
Developed mid-frequency trading strategies in Perpetual Futures Crypto market achieving Sharpe Ratio over 3, max drawdown 9.58% and live profitability.
Engineered Market Making algorithms across multiple crypto exchanges, incorporating market microstructure, liquidity provisioning, and inventory control
Applied custom Point Processes to model trade clustering and incoming order sizes, and SDEs with Non-Gaussian noise to simulate execution paths under realistic market dynamics
Incorporated stochastic optimal control theory for quote placement, risk-adjusted spread placement and dynamic quote sizing using atomic order book events data.

live strategies tradingmid-frequency trading strategiesMarket Making algorithmsPoint Processesstochastic optimal control theoryQuantitative Research+1

Auronova consulting

Research Intern

Jun 2024 – Aug 2024 · 2 mos · India · Remote

Strategized a comprehensive Merchant Recommendation Engine from scratch to boost user engagement, capture purchase intent, and drive transaction frequency by offering personalized merchant suggestions.
Capitalized the dynamic-correction architecture of Contextual Bandits to drive decision real-time and integrated intent-capture for more personalized experience, increasing the Evaluation Metric by 20%.
Business Impact: This solution addresses key business goals by continuously learning from interactions in real-
time. The model enhances customer satisfaction, retention, and loyalty, directly contributing to revenue growth
and a competitive edge in personalized user experiences.

Merchant Recommendation EngineContextual Banditsintent-captureMachine LearningData Science

Self-employed

Quantitative Researcher

Dec 2023 – Present · 2 yrs 6 mos

Researching options strategies leveraging rough volatility models (e.g., Rough Heston, Rough Bergomi) to capture skew, smile, and forward dynamics of the volatility surface.
Modelling vol surface evolution via fractional Brownian motion-based paths for better calibration under stochastic volatility regimes. Preliminary backtests suggest hedging error reductions of 20-30% compared to Black-Scholes-based methods.
Translating theoretical insights into automated Delta/Vega hedging algorithms and volatility arbitrage strategies. Volatility arbitrage strategies informed by rough volatility have historically generated modest excess returns (~5-7% annually) in academic studies.
Working on a rough volatility-based adaptation of a classical model that integrates jumps for more accurate modeling of fixed income instruments.
Designed and implemented a pairs trading strategy using cointegration and mean reversion techniques, achieving an average alpha of 2.59% and a final outperformance of 9.97% over NIFTY50 even during Bear market conditions.
Architected an options hedging strategy utilizing ATM straddles and OTM wings that delivered a Sharpe Ratio of 2.16, managed a maximum drawdown of 10%, and generated ~98% CAGR returns.

options strategiesrough volatility modelsDelta/Vega hedging algorithmspairs trading strategyoptions hedging strategyQuantitative Research+1