Help & Supportcareers@gravityer.com
Data Science with less than a year in Machine Learning & Data Analysis.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Piyush Korake is an aspiring Data Scientist currently pursuing a Master's degree in Statistics and Data Science. With 0.9 years of internship experience, he has developed strong skills in data analysis, machine learning model development, and business intelligence. He has actively contributed to projects involving multi-agent LLM frameworks, explainable AI, and portfolio optimization, demonstrating proficiency in Python, SQL, and various data visualization tools. Piyush is adept at transforming complex data into actionable insights for strategic decision-making.
Nilkamal School of Mathematics, Applied Statistics and Analytics, SVKM's NMIMS, Mumbai
Master of Science · Statistics and Data Science
August 1, 2023 – June 30, 2026
Fergusson College, Pune - 411004
Bachelor of Science · Statistics
August 1, 2019 – June 30, 2022
MAEERS MIT VGHS Pandharpur
Higher Secondary - 12th (HSC)
N/A – May 31, 2019
Rayat Shikshan Sanstha's, Yashwant Vidyalaya Bhose (K)
Secondary - 10th (SSC)
N/A – May 31, 2017
Opus Collect
Data Science Intern
February 1, 2026 – May 31, 2026
Navi Mumbai, Maharashtra, India
Yasham Software Services Pvt. Ltd.
Machine Learning Intern
July 1, 2024 – January 31, 2025
India
AI Trading Agent Simulation - Multi-Agent LLM Framework
July 1, 2025 – November 30, 2025
Built a sandboxed multi-agent LLM system with Researcher, Trader, Risk Manager, and Orchestrator. Implemented agent coordination and stateful workflows, with standardised tool access via MCP across isolated servers. Added logging, auditability, and observability to evaluate agent behaviour, execution errors, and end-to-end decision latency (~650 ms) during sandbox backtests.
Evaluating Explainable AI (XAI) Techniques Across Domains
December 1, 2024 – January 31, 2025
Applied SHAP, LIME, and PDP to interpret ML models across finance, healthcare, and retail domains. Built ML models with SMOTE to address class imbalance and explain feature contribution. Validated interpretability methods via practitioner surveys, confirming SHAP as the most effective technique.
Portfolio Enhancing: A Sectoral Approach
January 1, 2024 – April 30, 2024
Involved a comparative study of various models to analyse the Indian stock market. Examined a decade-long dataset of 389 large-cap companies listed for 2465 days, categorised into 11 sectors. Compared the Mean-Variance (MV) model for portfolio optimisation with the CVaR measure for risk management. Used a Monte Carlo simulation while evaluating rebalancing techniques to optimise stock allocation.
PCOS A Predictive Challenge
January 1, 2022 – April 30, 2022
Determined significant factors affecting PCOS using the Chi-square test and odds ratio. Performed Exploratory Factor analysis on the "Quality of Life" of women having PCOS. Built a predictive model with 89.7% accuracy for PCOS using regression.
Beginner: Introduction to Generative AI Learning Path
Unknown
June 1, 2026 – Present
Python for Data Science
IBM (via CognitiveClass.ai)
June 1, 2026 – Present
Cultural Fit Analysis
The candidate's academic projects demonstrate a diverse range of interests, from finance and healthcare to generative AI and traditional ML. The volunteer work indicates a commitment to community, which can be a positive cultural indicator. The breadth of skills and project types suggests adaptability and a willingness to explore different domains, aligning well with dynamic team environments. The target role of Data Science is well-aligned with the candidate's educational background and project experience.
Soft Skills & Operational Fit
The candidate's project descriptions indicate an ability to work on complex, multi-faceted problems, suggesting strong problem-solving and critical thinking skills. Involvement in a multi-agent LLM framework project implies an understanding of system design and coordination. The volunteer work and leadership course suggest good communication and teamwork potential. However, without direct interview data, the depth of these soft skills and operational fit cannot be fully assessed.