Apr 2023 – Jan 2025 · 1 yr 9 mos

• Leading a team of 12-14 engineers, Building & leading multiple products in Search, Personalisation & Recommendation Space using NLP, LLM, AI.
• Leadership :
• Managed a team of 6–8 engineers, driving 1:1s, career growth,
• coaching, and mentoring through situational leadership.
• Focused on keeping the team motivated by fostering mastery, purpose,
• and ownership.
• Successfully built two products—Chat and Recommendation—end-to-end from scratch along with managing existing search platform.
• Product :
• Building Paytm Super App Search Assistant
• (Supports vector search, api based retrieval, entity uid mapper, custom response mapper, text-to-sql)
• Deployed LLAMA2, 3 as a service/platform for internal use cases. Explored vllm, text generation inference etc., overall designed compute, response optimised solution.
• Built LLM + Deep Learning based multi lingual Intent Classification(70+ intents) and NER Detection for Indian Languages. Accuracy ~ 80% , 99th response time < 1 sec.
• Extending existing Search platform to support Voice & Semantic search use cases.
• Open Source LLAMA 2, LangChain, OpenAI, Transformers based models, BiLSTM, Multi Language Intent/NER handling, Transfer Learning & Fine Tuning.
• Building next version of User Personalisation platform. (Contextual MAB)
• Built a model to detect Indian languages from transliterated input. Accuracy ~ 80%
• Built a model to detect Indian names based on search input.(at prefix level). Accuracy ~ 75 %
• Built in-memory Low Latency Trie based spellchecker which gives suggestion at prefix level, also uses phonetic sound, performance metrics, keyboard distance to give spell suggestions.
• 99.9 response < 20 ms

Apr 2022 – Mar 2023 · 11 mos

• 6+ million search hits per day, 150+ million monthly active users, 20+ million merchants.
• Leading a team of 6-8 engineers, and building multiple Search Products( ONDC Search, Federated Search Platform, Location Aware Search, Search As You Type, Autosuggestion etc.)
• Making sure that we have highly available, fault-tolerant, highly scalable, elastic, low latency systems.
• 99th Response < 50 ms
• Serving millions of requests every day.
• 0. Building something exciting in NLP space for scale.
• Transformers, BiLSTM, Multi Language handling, NER, ChatGPT etc.
• 1. Migrated ES cluster from ec2 to k8 setup with zero downtime, and keeping 100% data consistency.
• 2. SpellChecker for Search-As-You-Type Platform(Spell Correction at Prefix level).
• 3. Rearchitected Paytm Search Platform(Federated Search) to support vertical specific Search Experience.(No downtime, keeping 100% data consistency)
• 4. Built Geo Hash based location filtered Search.
• 5. Built ONDC Search/Discovery Platform (Location Aware Search)
• 6. Built offline Search Relevance Measuring system, which can verify/figure out the correctness of test search approach.
• Elastic search, Node, Typescript, Python, Django, uWsgi, Java, Springboot, Kafka, MySql, Performance Optimisation

Jan 2021 – Apr 2022 · 1 yr 3 mos

• Paytm Search
• 150+ mn monthly active users, 20+ mn merchants.
• Leading the development team/building multiple Search products for millions of users.
• 1. Built/Led the development of Paytm Search V2.0 experience from scratch. (Search As You Type)
• 2. Built/set up elastic cluster from scratch, lot of benchmarking to get required SLA, making sure that we have highly available, fault-tolerant, highly scalable, elastic, low latency system.
• Response_99 < 60 ms,
• Serving millions of requests every day.
• 3. Worked on solving multiple Search Space problems from scratch for millions of users. (catalog with millions of docs, serves millions of search requests per day. )
• 4. Took lots of tech initiatives/POC in terms of trying new technologies, tools and making awareness on using it.
• 5. Lots of work around breaking existing Search Systems into multiple micro-services with DDD(Domain Driven Design), separation of concerns, reusability, focusing on choosing the right tech stack etc.
• 6. Lots of work around benchmarking, performance engineering, making sure that we respond in minimal time(response 99 < 65 ms)
• Apache AB, ESRally
• 7. Re-Built existing search classifier to framework model which can run multiple versions of classifier without any code changes. Making sure that Response_99 < 6 ms
• 8. User-based A/B framework, serving millions of requests every day.
• Elastic search, Node, Typescript, Python, Django, uWsgi, Java, Springboot, Kafka, MySql, Performance Optimisation

Oct 2020 – Nov 2020 · 1 mo · Bengaluru Urban, Karnataka, India

• Coviam v2.0 | Blibli(https://www.blibli.com/)
• Loved my journey at Coviam/Quinbay(Blibli.com), learned lot of things here :)
• 1. Worked on building distributed, event driven, fault tolerant and highly scalable data auditing system which can be used across all the services.
• 2. Also worked on setting up search interface for getting the audit data using ElasticSearch.

Jan 2020 – Sep 2020 · 8 mos · Bengaluru Area, India

• Blibli(https://www.blibli.com/)
• 1. Worked on building Blibli.com B2B E-Commerce platform from scratch(Sales order creation, order approval, order creation, order fulfilment etc.) Worked with 6 other engineers, and led the technical direction of product .
• Worked on setting up all the required micro-services from scratch eg: order, customer, product, cart, finance etc, setup end to end data pipeline for the same.
• java, springboot, kafka, mongodb, postgres, redis, gcp, consul, vault.
• 2. Working on building catalog management system for Blibli.com Tivo(Ticket and voucher) which takes care of multiple use cases eg: profit configuration, inventory management, catalog management, data auditing etc.
• java, project reactor, kafka, elastic search, mongodb, springboot, gcp, consul, vault

Nov 2018 – Aug 2019 · 9 mos

• Blibli(https://www.blibli.com/)
• 1. Worked on creating highly scalable Promo creation systems.(which touches multiple services eg: cart, search, product, pricing, merchant etc.)
• 2. Worked on building Promo Scheduler, Email Scheduler.
• 3. Worked on Price Scheduling, Price Indexing, Dynamic Pricing.
• 4. Worked on setting up services for moving to gcp(consul, vault, docker, kubernetes ).
• 5. Worked on upgrading Mongo DB from 3.2.18 to 4.0.3 for catalog system.

Jul 2017 – Oct 2018 · 1 yr 3 mos

• Blibli.com
• Worked on core services of Indonesian Ecommerce(Blibli.com).
• Spring data, Spring boot , redis, mongodb, kafka, scala, play framework, Solr, Microservices.
• 1. Worked on adding new payment methods for various banks.
• 2. Worked on building order summary apis for merchant side users. (Scala, Play)
• 3. Worked on building Birthday rewards feature which sends voucher to customers.
• 4. Worked on building generic, distributed crawling framework which allows to extract products information for various product sources/ecommerce sites.
• 5. Worked on building generic data extraction/massager framework.
• 6. Worked on building real time price comparison application which works for various categories eg: handphone, computer, camera, health & food, drink, washing machine, tv, refrigerator.
• 7. Worked on building distributed multi mapping recommendation feature which gives multiple master products recommendation for given merchant product.

Aug 2019 – Dec 2019 · 4 mos · Bangalore Urban, Karnataka, India

• Joined as 6th member of tech team, worked on building Master Address system,
• Delivery Assist system.
• Python, Django, Postgres, aws lambda

Mar 2016 – Jul 2017 · 1 yr 4 mos · Bengaluru Area, India

• My work here involves Machine learning, struts2, objective c, javascript, jquery, weblogic.
• Worked on on various JD Edwards mobile IOS and android application issues.
• Working on Oracle hybrid mobile - MAF framework.
• Also handling AIS server issues which provides interface to the rest services for jde.

May 2015 – Mar 2016 · 10 mos · Bengaluru Area, India

• Was part of Cerner Revenue Cycle team. Worked on building multiple features eg: appointment interaction etc.
• Java Rcp, Sql, Cerner command language.

Jan 2015 – May 2015 · 4 mos · Bengaluru Area, India

• Worked on WPF and CCL.

May 2014 – Jun 2014 · 1 mo · Bangalore

• Worked on JAVA STRUTS-2