Hello, I'm Kiran

Building the Future with
Artificial Intelligence

  • Applied AI ML Lead, Vice President at JPMorgan Chase, Hyderabad, India.
  • Data Science Lead with 13 Years in IT, including 10+ Years in Data Science and 5 years in technical leadership.
  • Led a team of 4 data scientists growing ads revenue; built foundation models, ranking and recommendation systems, and AI agents.
View Resume
Download PDF
Total Experience
13 Years
10+ Years in Data Science
Current Role
Vice President
Applied AI ML Lead

Professional Experience

Applied AI ML Lead - Vice President
JPMorgan Chase
Jul 2024 - Present
  • Developed the Chase Customer Foundational Model as part of an org-wide initiative: a 38M-parameter transformer backbone with masked and next-event pre-training. Built training data from 52B+ card, deposit, digital and offer events within a base of 95M+ customers; trained on 24 H100 GPUs (Ray, 3 nodes) to generate 512-d customer embeddings for downstream risk modeling, fraud detection, and category selection and ranking.
  • Re-architected and developed the category selection and ranking model; evaluated 8 challenger models, including SAINT and FT-Transformer, against contextual-bandit LinUCB and deployed distributed inference on Ray Serve.
  • Migrated and deployed the Account Origination Model on Databricks/MLflow for 49 products, with monthly retraining and champion/challenger releases; moved 95M-customer batch scoring from Spark/EMR to Ray Data, 3.7x faster.
  • Developed the Marketing Automation Agent, a LangGraph/Bedrock audience-selection agent translating marketing goals into catalog-grounded features, SQL and modeling plans through multi-query RAG and parallel retrieval.
  • Developed a customer-level email opt-out risk model using contact frequency, engagement and dormancy signals to predict next-week unsubscribes and inform audience prioritization and contact-policy decisions.
  • Fine-tuned SLMs to detect paycheck and rent transactions using a 577K-pattern silver dataset labeled with Ministral 3 8B; evaluated on human-labeled holdouts to support downstream insight generation.
  • Created an AutoResearch agent for LLM-driven experiment loops and co-built Casper, a multi-agent VS Code extension for Jira, Confluence and Bitbucket; both are used by ML and engineering teams across CCB Digital.
Senior Lead Data Scientist
Tokopedia
Dec 2021 - Jul 2024
  • Led 2 data science projects - Ads Ranking and Keyword Recommendation, managed 4 data scientists and delivered high-quality data science solutions for TopAds business problems.
  • Developed Real-time Ads Ranking (RTR) system, achieving 3.25% increase in CTR, 1.57% increase in Ads Revenue (~1.6 billion IDR) and deployed scalable, low latency model inference pipeline, to achieve sub 80 ms latency with 1K requests served per second.
  • Optimised inference of an existing deep learning solution using post-training quantization techniques which increased revenue by 1.43% (1.4 billion IDR monthly) and saved inference costs up to 166 million IDR monthly.
Data Scientist
ADP
Nov 2019 - Dec 2021
  • Built machine learning models for Job Classification and PayCode Classification in the ADP DataCloud team.
  • Implemented multi-lingual Job Classification model using Language Agnostic BERT (LaBSE) & multi-lingual Universal Sentence Encoder (mUSE), reducing time to market from 6 to 2 months.
  • Deployed models on AWS using Step Functions, ECR, Sagemaker Endpoint and API Gateway as batch transform pipelines and real-time endpoints, scaling model serving capacity by 3x to handle increased inference requests.
Data Scientist
DBS Bank
Oct 2017 - Oct 2019
  • Built machine learning models for Cash In Transit and Cheque Analytics in the Self-Service Banking, CBG group.
  • Implemented binary classifier using LightGBM for Cheque Risk Scoring model, to provide a risk score for all inward cheques, reduced false negatives by 18% through effective handling of class imbalance.
  • Forecasted no-cash situations for ATM, BTM, and CRS cash withdrawals using FB Prophet for time-series forecasting, resulting in a 15% reduction in cash shortage incidents.
Software Engineer
Tech Mahindra
Nov 2013 - Oct 2017
  • Worked as a Software Engineer for General Electric (GE) client in 4 different projects spanning from data ingestion to data science.
  • Engineered a Cash Collection ML model using clustering to segment customers based on payment behavior, decision trees to predict the likelihood of timely payments and GE US Payroll model using ARIMA.
  • Integrated JSON data from APIs to R dataframes and CSV, developed Talend jobs for data integration.

Technical Skills

GenAI & Agents

LLMs
SLMs
Fine-tuning (LoRA, PEFT)
Agentic RAG
Context Engineering
Multi-agent Systems
MCP

ML & DL

RecSys & Ranking
NLP
Forecasting
Embeddings
Foundation Models
Quantization
A/B Testing

Languages & Frameworks

Python
R
SQL
PyTorch
TensorFlow
Hugging Face
scikit-learn
LangGraph
LangChain

Cloud & MLOps

AWS (Bedrock, SageMaker)
GCP (Vertex AI)
Databricks (MLflow)
PySpark
Ray (Ray Serve)

Education

Bachelor of Technology (B.Tech)
GITAM University
2009 - 2013

Electronics and Communications Engineering (ECE). Graduated with 8.4 CGPA.

Courses

Summer School on NLP
IIIT Hyderabad
Jun 2024

Attended Summer School on NLP with focus on Large Language Models (LLM) and Natural Language Generation (NLG) conducted by LTRC, IIIT Hyderabad.

Summer School on CV and DL
IIIT Hyderabad
Jul 2018

Attended Summer School on Computer Vision and Deep Learning conducted by CVIT, IIIT Hyderabad.

Awards

Best Summer School Project
IIIT Hyderabad
Jul 2024

Awarded 2nd place for Continued Pre-training of LLM on Legal Contracts - LLM Domain Adaptation project.

Super Techie
DBS Bank
Dec 2018

Awarded the Pride Connect Award for being the Super Techie at C2E, Consumer Banking Analytics.

Workplace Catalyst
DBS Bank
Jul 2018

Awarded for being a part of the team which is Workplace Catalyst across the whole DBS Tech Organisation.

Personal Interests

When not making a difference in the world, I spend a significant amount of leisure time

Lets connect on LinkedIn .

Peace!