Rachit Tripathi

Co-Founder

Bengaluru, Karnataka, India6 yrs 3 mos experience

Highly Stable

Key Highlights

Expert in machine learning applications in finance.
Co-founder of a startup focused on investment decisions.
Strong background in quantitative analysis and model performance.

Stackforce AI infers this person is a Fintech expert with a strong focus on quantitative analysis and machine learning.

Contact

rachit340@gmail.com LinkedIn

Skills

Core Skills

Machine LearningData ScienceStatistical ModelingModel Governance

Other Skills

AlgorithmsApplied Machine LearningArtificial Neural NetworksCC++Computer VisionData AnalysisData AnalyticsDeep LearningFinanceFinancial ModelingGaussian Process RegressionHadoopKerasLaTeX

About

Currently enrolled in top-ranked UC Berkeley Master of Financial Engineering program. Interested in data science/quant research role. Experienced in applying machine learning and statistical modeling techniques to solve problems in finance. Enjoy doing data science competitions.

Experience

Blacklitt technologies pvt ltd

Co-Founder

Oct 2025 – Present · 5 mos · Bangalore Urban, Karnataka, India · On-site

Building Blacklitt to help smart Indians make better investment decisions.

Goldman sachs

3 roles

Vice President

Promoted

Jan 2025 – Apr 2025 · 3 mos

Associate

Promoted

Aug 2023 – Dec 2024 · 1 yr 4 mos

Portfolio Manager within Multi Asset Solutions (MAS) business.

Associate

Jul 2022 – Aug 2023 · 1 yr 1 mo

GSAM: Quantitative Equity Solutions

Temasek

Project Intern, Quantitative Strategies

Oct 2021 – Mar 2022 · 5 mos · San Francisco, California, United States

Hsbc global banking and markets

Quantitative Analyst - Markets Front Office

Feb 2018 – Feb 2021 · 3 yrs · Banglore

Part of Structured Rates quants responsible for data science projects and model performance monitoring in the team.
VaR approximation project:
Developed machine learning based model to approximate VaR calculations for structured rates portfolio.
Reduced the computation time and computation cost by 80% while maintaining VaR error to be within 0.1% percent.
Model implemented using In-house built algorithms and Gaussian process regression.
Model Performance Monitoring Scripts:
Implemented 9 model performance monitoring scripts in python to monitor model risk.
Scope of scripts include the stability and profile of associated risks which are essential tools Model Governance.
Models associated with these monitoring are: Spread Option Pricer (MultiSABR), Multiple Underlying Black Scholes (MUBS), Inflation Curve Construction and Cheapest to Deliver (CTD).