MerQube is an innovative fintech firm, leading the development of cutting edge technology for indexing and rules-based investing. MerQube designs and calculates a wide variety of indices, ranging from thematic to ESG, factor and retirement, while covering multi-asset, equities, futures as well as options. Few highlights of my role here are:

• Engineered the migration of equity reference and end-of-day pricing pipelines to a new provider platform, ensuring uninterrupted data delivery for index calculations with zero downtime.

• Led the development of a scalable options data platform, defining the data model, building ingestion and monitoring systems, and partnering with product, data providers, and financial engineers to resolve complex data integrity challenges. Delivered a unified data access layer that powers multi-asset index development and self-service analytics across teams.

• Transformed operations workflow by developing automated validation checks for end-of-day prices and corporate action data across multiple providers. Enhanced data accuracy and consistency with customizable override capabilities.

Fall 2022 and Spring 2023 - Deep Learning by Prof. Alfredo Canziani & Yann Lecun.

Zipline designs, manufactures and operates the world’s largest autonomous drone delivery network, enabling on-demand logistics of essentials, from medical supplies to consumer goods, at unprecedented speed and scale. Few highlights of my role here were:

• Building perception software as part of the acoustic detect and avoid team to answer a specific question, How to tune the current encounter detection models to be resilient to changes in sensor environment, in order to decrease the false positive rate.

• Analysed flight data at production nests, to find spatial and temporal correlation for locating probable sources of false positives.

• Fine tuned intruder detection models using hard negative samples to reduce false positives by 70% on production nests while having minimal impact on sensitivity.

Karza Technologies (Now Acquired by Perfios) was a data, analytics, automation, and decisioning solution provider to FIs, catering to the entire lending lifecycle from onboarding to diligence & monitoring to collections. Karza Technologies solutions enable systemic fraud prevention, risk management, compliance & automation through superior data engineering and deep tech applications.

Few highlights of my role at Karza were:

• Developed an end to end OCR Pipeline for the KYC Documents by implementing a robust synthetic data generation pipeline, model validation, hypothesis testing and training modules for text recognition, card detection and text detection tasks.

• Light weight reformulation of fixed length text recognition model using the CTC framework and TensorRT for weight quantization to decrease model size by 85\% while maintaining almost the same accuracy level, so that it could be deployed as AWS Lambda service.

• Progressively optimized the OCR task specific models bridging the latency vs task specific evaluation metric tradeoff (like word and character accuracy for text recognition).