Akaike (A boutique data science consulting startup) | Bengaluru

Principal Data Scientist

• Established and led a 3-member consulting vertical and secured first client win which brought ~$250K in revenue.
• Pitched and delivered a cross channel next best action system to a pharma client; architected an ML system that drove $20M/disease area/annum/region impact across top 3 brands.
• Led delivery of claim code extractor as its Engagement Manager - augmenting a ~3-person, month-long manual process with an automated pipeline, achieving 80% OPEX reduction and ~90% team adoption.
• Led demand forecasting for a QSR startup, driving 20% topline growth and 45% waste reduction; also led HSI-based object detection for a Defense client coaching the team on specialized CV methodologies and workflows.
• Managed a 12-member cross-functional data science team (5 tiers), running regular retros for team health checks and monthly 1:1s for bidirectional feedback and junior talent development.
• Overhauled the DS hiring process cutting hiring TAT from ~10 weeks to ~3 weeks through unified evaluation framework, structured round formats etc.
• Revamped two-way performance review to a 360-degree system reducing review complaints and democratizing feedback beyond reporting manager.
• Built and institutionalized an assetization (IP) framework, successfully assetizing 10+ projects significantly accelerating deployment of the same on other clients.
• Led HSI-based object detection for a client in Defense sector - directing model design and annotation for 4-5GB hyperspectral satellite imagery, coaching the team on specialized CV methodologies uncommon in standard workflows.

McKinsey & Co. (A multinational strategy and management consulting firm) | Gurugram

Sr. Analyst, Expert Consulting

• Led Fleet Optimization for an Oil & Gas major in South America - formulating a LP-based allocation model with Monte Carlo sensitivity analysis, driving ~$30M OPEX reduction; was deployed to Malaysia for client capacity building and authored a whitepaper which was eventually used as a foundation for an internal firm asset.
• Led anode tracking system building a multi-stage computer vision pipeline achieving 92% tracking rate at an aluminium smelter in middle east.
• Built Total Commercial Spend Optimization - prescriptive ML model for an Indian Lifesciences major - layering an optimization routine over an MMM model (AdStock, Hill Saturation, Bayesian tuning) across Linear Regression and GAM archetypes, with a post-engagement whitepaper repurposed as a firm-wide asset.
• Spearheaded FinX - a transaction analytics accelerator with classification accuracy of ~95% through a custom neural network architecture. It was also deployed downstream for a major South American bank in fraud detection use case.

Fellow - Data Science

• Led credit risk models for Banks and NBFC majors resulting in 40%+ GINI and ~85% reduction in decisioning TAT.
• Built PySlice - a credit risk modelling accelerator cutting first-cut model development from 3 months to 1 week, which was utilised across 10+ banking engagements.
• Led anode tracking system building a multi-stage computer vision pipeline achieving 92% tracking rate at an aluminium smelter in middle east.

Roadzen (AI-driven platform in auto insurance and mobility space) | New Delhi

Data Scientist

• Built a custom OCR system - reducing inspector form-filling time and driving ~300% throughput increase.
• Designed a human-mimicking KV- extraction framework for 200+ policy document layouts - building a config-driven, end-to-end PDF processing engine capable of extracting key-value pairs in seconds per document.
• Built an internal DL classification accelerator - cutting first-cut model experimentation TAT by 85%.
• Led and streamlined the annotation pipeline, coordinating a 12-member annotation team for ground truth labelling.

Nissan Digital (Nissan's digital innovation center in India) | Trivandrum

AI Engineer, Data Science CoE

• Led demand forecasting for 9 car models across NNA and Japan, improving MAPE by 26% driving 8% inventory cost reduction (~$100M savings).
• Led end-to-end deployment of a CV-based corrosion detection system on the factory floor - from camera setup and annotation to training deep learning models - doubling inspection throughput and significantly improving quality.
• Built a kiosk-based car recommendation engine (Recall@10: 63%) with a custom de-clustering algorithm for granular outputs, integrated into the customer-facing kiosk in collaboration with UX/UI, Data Engineering, and Software Engineering teams.
• Led the development of predictive maintenance system reducing overhaul incidences by ~40%.
• Represented Data Science CoE at conferences and university visits, strengthening talent pipeline and employer brand.

• Promoted from Fellow to Sr. Analyst within 1 year of joining McKinsey (Joining: Jan’22, Promoted in Dec’22).
• Gave a 5 hour conference talk on time series forecasting at GIDS, 2020, titled “Little Data, Huge Expectations”.
• Created two open-source libraries:
  • swtLOC: A python Implementation of Stroke Width Transform algorithm from Microsoft Research, Detecting Text in Natural Scenes with Stroke Width Transform, 2010.
  • tsEuler: A python Library for time series analysis dashboard.

• Bachelors in Technology (Electrical Engineering), Jamia Millia Islamia, 2018.

• Post Graduate Diploma in Applied Statistics, IGNOU, 2021
• Deep Learning Specialization, Deeplearning.ai, 2019
• Machine Learning, Stanford, 2019
• Mathematics for Machine Learning, Imperial College, 2019
• Qiskit Global Summer School on Quantum Machine Learning, IBM, 2021

• Successfully trekked to Everest Base Camp (5364 mt) in December’23 and Summitted Kala Patthar (5700 mt) in December’23.