Harshit Sharma

Associate Consultant

Bengaluru, Karnataka, India5 yrs experience
Highly Stable

Key Highlights

  • Engineered a real-time risk engine processing 10M+ packets/day.
  • Architected a central lakehouse reducing BI query latency to under 5 minutes.
  • Migrated credit-risk models achieving 93% model parity.
Stackforce AI infers this person is a Fintech and Agritech expert specializing in data engineering and quantitative analytics.

Contact

Skills

Core Skills

Quantitative FinanceData EngineeringRisk ModelingMachine LearningFinancial ModelingRobotics

Other Skills

Apache AirflowApache FlinkApache IcebergApache SparkBig DataC++CassandraCeph S3ClickHouseCommercial BankingComputer VisionData ModelingData PipelinesETLFinance

About

Software Engineer specializing in data engineering, quantitative analytics, and risk modelling. Pursued a B.Tech in Computer Science and Engineering from the IIT (ISM), Dhanbad (Class of 2024) At the Unique Identification Authority of India (UIDAI), I’ve been building and scaling data-intensive national scale systems that power analytical and operational intelligence across petabyte-scale datasets: - Designed a PySpark-based multivariate risk engine processing 10M+ packets/day, achieving 90%+ anomaly detection precision and reducing fraud losses - Built Python and Spark based services and deployed Frameworks, databases, tools on Kubernetes - Developed predictive analytics pipelines with stage-wise SLA breach prevention, employing Gradient Boosting Models (GBM) on GCP for proactive risk detection - Core tech stack includes: Python, Spark, SQL, Trino, Kafka, Airflow, Kubernetes, ClickHouse, Cassandra, Hive, Iceberg, S3, Redis Earlier at Axis Bank, I worked on multiple loan risk model migrations from SAS to PySpark.. Beyond work, I explore quantitative research and financial modeling, developing cross-asset trading strategies, multithreaded market data aggregation systems in C++, and statistical alpha models. I’ve applied techniques from Monte Carlo simulation, CAPM, and option pricing (Black-Scholes) to evaluate portfolio performance and risk-adjusted returns. I’m passionate about the intersection of data systems, quantitative modeling, and intelligent risk analytics, leveraging computation, mathematics, and data to power better financial and real-world decision-making.

Experience

5 yrs
Total Experience
3 yrs
Average Tenure
1 yr 11 mos
Current Experience

Worldquant

Quantitative Research Consultant

Apr 2025Present · 1 yr 2 mos · Remote

Quantitative Finance

Unique identification authority of india (uidai)

Software Engineer

Jul 2024Present · 1 yr 11 mos · Bengaluru, Karnataka, India · On-site

  • Engineered a real-time, multivariate risk engine using PySpark, combining historical and live time-series signals to score 10M+ packets/day. Integrated statistical indicators (Z-score, covariance, deviation) to enhance fraud detection precision by 90%+, enabling adaptive downstream responses.
  • Architected UIDAI’s central lakehouse (Apache Iceberg + Hive + S3) unifying heterogeneous data streams and reducing BI query latency from hours to under 5 minutes, powering nationwide analytics workloads
  • Built an Aadhaar billing computation service over 1.6T+ records, enabling automated cost attribution and reducing processing time from 7 days to 8 minutes with SparkSQL optimizations
  • Deployed ClickHouse as a high-performance OLAP layer, achieving a 200% boost in query performance through schema normalization, memory-mapped I/O optimization, and compute-aware configuration tuning.
  • Automated Flink table compaction and Spark job orchestration via Airflow with dynamic, YAML-driven templates, establishing a modular, low-code data pipeline framework
  • Implemented predictive analytics pipelines using Gradient Boosting Models (GBM) on GCP, performing stage-wise SLA breach prediction and proactive anomaly detection to improve system reliability
Apache SparkRisk ModelingStatistical Data AnalysisPySparkBig DataKubernetes+15

Active growth partners

Data Science and Software Developer

May 2024Jul 2024 · 2 mos · Remote

Axis bank

Data Engineer

May 2023Jul 2023 · 2 mos · Mumbai, Maharashtra, India · On-site

  • Migrated credit-risk models from SAS to PySpark, achieving 93% model parity and reducing processing time by 80%.
  • Developed ETL lineage tracking flows to monitor data flow, resulting in a 20% decrease in pipeline errors.
  • Enhanced algorithms and data structures to optimize performance while gaining foundational knowledge in finance.
SAS (Programming Language)PySparkFinancial ModelingBig DataStatistical Data AnalysisSQL+3

Indian institute of technology (indian school of mines), dhanbad

Contingent Leader, Inter-IIT Tech Meet 11.0

Dec 2022Feb 2023 · 2 mos

Nvcti

Product Development Intern

May 2022Jul 2023 · 1 yr 2 mos · IIT ISM Dhanbad · On-site

  • Developed a commercial product to aide in the agricultural industry by automating the task of collecting the agricultural produce and readying it for transport using the combination of UAVs and UGVs
  • UAV and UGV were using visual SLAM algorithm to map the area and work autonomously to pick and place stacks.
ROSGazeboSLAMPixHawkPythonRobotics

Roboism - robotics and artificial intelligence club

Coordinator

Apr 2021May 2024 · 3 yrs 1 mo · Dhanbad, Jharkhand, India

SOLIDWORKSRobot Operating System (ROS)Machine LearningcC++Python (Programming Language)+1

Education

Indian Institute of Technology (Indian School of Mines), Dhanbad

Bachelor of Technology - BTech — Computer Science

Jan 2020Jan 2024

Indian Institute of Technology (Indian School of Mines), Dhanbad

Minor — Robotics Technology

Jun 2022Dec 2023

Maa Bharti sen sec school SVN kota

High School/Secondary Certificate Programs

Jan 2018Jan 2020

Mayoor School, Ajmer

IGCSE O Levels

Jan 2005Jan 2018

Stackforce found 100+ more professionals with Quantitative Finance & Data Engineering

Explore similar profiles based on matching skills and experience