Kamesh Chandran

Engineering Leader, Fraud & Risk Systems

About Me

20+ years in engineering, the last few leading ML and data engineering for Grab’s Trust, Identity & Safety team in Singapore. I build the fraud detection models and data pipelines that watch transactions across Grab’s platform. Lately that work has shifted toward LLM applications: device checks, tamper detection, automated fraud reporting, and most of my own coding now runs through agents like Claude Code. Before Grab I built banking, e-commerce and aerospace platforms, which is where the systems design habits come from.

Core Competencies:

Engineering Leadership

  • Led teams of up to 10 engineers across fraud detection, data platform and portal projects, from design through production support
  • Pushed LLM-assisted development and agentic workflows into the team’s daily practice, starting from my own experiments
  • Data Architect for enterprise-scale data lakes and warehouses; Solution Architect on AWS cloud native systems
  • Take ambiguous problems and own them until they ship

AI Engineering & LLM Tooling

  • Prompt engineering and RAG systems, running in production
  • ML pipelines built with MLOps practices, from training through monitoring
  • Autonomous agents for business process automation, plus agentic workflow experiments with OpenAI and Hermes-family frameworks
  • Daily driver tools: Claude Code, Cursor, Codex

Domain Expertise

  • Fraud Detection & Risk Management - real-time ML scoring transactions across 8 business lines
  • AI-powered products - LLM applications, agents and internal AI tooling in production
  • Banking Systems (Merchant & Customer Portals)
  • Order Management & E-commerce
  • Data Center Operations
  • REST-based Middleware & Microservices

Experience

Grab

Lead Data Engineer, Trust, Identity & Safety

September 2021 - Present

grab.com

Grab - the leading super app in Southeast Asia - combines transport, food delivery, logistics, financial services, and much more in a single platform and its mobile application in Cambodia, Indonesia, Malaysia, Myanmar, the Philippines, Singapore, Thailand, and Vietnam. The company is headquartered in Singapore

The TIS (Trust, Identity & Safety) department acts as guardians of all users on Grab. It closely monitors every event such as account login, booking and transactions on the platform for over 8 major business lines across Grab, making data driven decisions in milliseconds. I lead the machine learning and data engineering behind that: the models that score transactions in real time, and the tooling the investigators use on the cases those models flag.

Modules Lead and contributed:

  • Work on problems that run the gamut from data science to deploying and monitoring models in production.
  • Build and deploy machine learning models for fraud, risk and safety. Scam rings across Southeast Asia keep getting more organized and automated, which has made fraud detection one of Grab’s most closely watched business lines.
  • Automated Modus Operandi (MO) reports, turning raw case data into the story of how a scam actually played out. Investigators used to piece that together by hand.
  • Designed and maintain the LLM applications running in production: device information analysis, food preference inference, and tamper detection that catches cloned apps, auto-clickers and other scripted abuse before it reaches real users.
  • Prototyped agentic workflows with OpenAI and Hermes-family agent frameworks, including a Slack bot that pulls fraud signals on demand.
  • Analyze data and define metrics for feature evaluation and model performance.
  • Design and implement robust data pipelines.
  • Identify and build new approaches and methods for machine learning as we grow.
  • Do most day-to-day coding with Claude Code, Cursor and Codex.
  • Framework and technical: Java 11, Scala, Flink, Elasticsearch, Kafka Streaming, Terragrunt, AWS EC2, S3 and DynamoDB.

Equinix

Senior Staff Engineer (Lead Engineer)

December 2015 - September 2021

customerportal.equinix.com

Equinix's single global platform helped digital leaders stay out front for more than 20 years. Interconnect your digital infrastructure to scale with agility, leveraging leading enterprises and service providers in ecosystems that multiply value for all. At Equinix, we see every day as a fresh opportunity to help you fast track your digital advantage.

Equinix’s Colocations platform provides interconnections between digital enterprises. Customers can buy colocation services and handle everything after the sale, billing included, in one platform, reached through web, mobile, or a partner API. Six years on the hardest problems the data center industry had to offer.

Modules Lead and contributed:

  • Enterprise Search Engine - a permission driven search engine that lets users run multilingual queries to find relevant information. Relevancy and ranking are tuned against business domain fields rather than generic text scoring, so results match what customers were actually looking for.
  • Unified Notifications service - one notification layer in front of firebase, MS teams, Azure queue, SMS, and email, replacing the per-channel integrations scattered across the platform.
  • Interconnection LOA management - the approval process that establishes a connection between two customers.
  • Machine learnings projects
    • Smart Discovery - reads the attachment content or request description and recommends the order type, then pre-populates the details the user would otherwise fill in by hand.
    • Order Recommendation - predicts dependent orders from frequent action patterns, so placing a connected order takes fewer clicks.

FIS (Fidelity National Information Services)

Technical Lead Engineer

July 2014 - December 2015

fisglobal.com

FIS stays ahead of how the world is evolving to power businesses, across merchants, banking and capital markets, to outpace today’s fast-changing competitive landscape and help our clients run, grow and achieve more for their business.

FIS needed online banking solutions so buyers and sellers could check balances and make payments. I was the lead engineer on the generic portal layer that let merchants and customers view and manage any transaction life cycle, shipped to FIS customers as an out of the box product with white labeling. A short stretch, 1.6 years, that packed in a lot of banking domain experience.

Modules Lead and contributed:

  • Merchant Portal - handles mPOS device association for sellers and lets them manage settled transactions and refunds. Built as an Angular JS single page application over middleware in Spring 4.x, Java 8 and Nginx.
  • Prepaid Customer Portal (Mobile wallet) - balance, top-up and transaction history for prepaid wallet holders, sharing the portal platform and white labeling layer with the merchant product.
  • OTP platform Service - one time password solutions used as 2 factor authentications for any payment authorizations or authorizing user for verifications. The frameworks use in this project are Apache Camel, Scala, SMS Gateway services.
  • POC:
    • Aadhaar based KYC approval for customer - opening a bank account from an Aadhaar linked mobile number and a fingerprint capture. The frameworks use in this project are Angular JS, Apache Cordova, finger print scanner, android.

HTSL (Honeywell Technology Solutions Lab)

Technical Lead Engineer

July 2006 - April 2014

aerospace.honeywell.com

Honeywell Technology Solutions Lab Private Limited is a computer software company

Nearly eight years on Honeywell’s aerospace customer platform. The portal handles airplane product orders and warranty for Honeywell aerospace offerings, lets engineers download engine technical documentation, and takes payment for rented engines and services. Five of those years I was technical lead of a 10 person team, plus 16 months as on-site coordinator, two years as an engineer and six months as an intern trainee. This is where I learned to lead engineers, and I spent a lot of it evaluating technology and pushing for better solutions.

Modules Lead and contributed:

  • Aerospace Portal - the main web portal for Honeywell Aerospace customers and customer support representatives to place orders, collate information on an order, download technical documents, and search for field service engineers and support locations. Built on Websphere Portal 7, Spring Portlets and generic portlets.
  • SHARED Portal Migration - migrated SHARED system functionality into the MyAerospace portal so Honeywell’s airline customers could reach value-added aftermarket service for their MRO requirements. Built on Spring 3.x, MyBatis, Ajax and Websphere portal server.
  • Plymouth Migration - reselling portal where customers and employees search and browse the catalog, add to cart and place an order. The frameworks used in this project are SAP ECC eSelling, XCM, NWDS.
  • ATR Catalog - put the ATR catalog on any mobile device for Honeywell’s internal sales reps, configurable and downloadable so it persists on the device. Useful when they are out at an Aero show conference.
  • Other Projects
    • HSCE - Honeywell Health and Safety system Portal
    • Teardown Management system - Barcode generation, for comparing LCD productions for Honeywell Patterns
    • HonBoard - Online whiteboard solutions like “Miro”
    • Catalogic - IPad Applications for Aerospace Catalog for sales and marketing.
    • Integrated Supply chain - SAP Enterprise Portal Solution based for Supply chain management.
    • Single Sign On Integration - using saml defining authorizations and authentications between multiple systems

Education

The University of Texas at Austin, Executive Education

Post Graduate certificate Program - Artificial intelligence and Machine learning

2019 - 2020

eportfolio.greatlearning.in/kamesh

The University of Texas at Austin, shortened to UT Austin, UT, or Texas, is a public research university in Austin, Texas and the flagship institution of the University of Texas System.

I went back to school for machine learning after a decade of platform engineering. Cleansing data for model prediction, PCA, feature engineering, then building and managing the models themselves. The part that stuck was learning to read a business use case well enough to know what you are actually predicting.

JJ College of Engineering (Affiliated to Anna University)

BE Computer Science

2003 - 2006

JJ College of Engineering, affiliated to Anna University

Committee member of the College Developer Community, where I arranged hacking sessions for juniors, organized hackathons and served as Cultural Event Vice-President.

Department of Technical Education

Diploma in Computer Technology

2000 - 2003

KAR Polytechnic college, Ambur, Tamilnadu, India

A Little More About Me

Alongside my interests in AI, ML and software engineering some of my other interests and hobbies are:

  • Running
  • Writing blogs link
  • Grab engineering blogs link