Summary
Overview
Work History
Education
Skills
Timeline
background-images

Ravi Ranjan

Banglore

Summary

Creating and Scaling the AI platform of a leading CRM company serving fortune 500 clients. Past experience includes scaling and optimising the supply chain of leading grocery portal, have a high paced development background of 11 years including design, architect and code from scratch to create complex scalable SOA , Big Data systems including Machine and Deep learning/AI at scale. I also managed a team upto 15 people to deliver the product in time with best development principles.

Overview

13
13
years of professional experience

Work History

Engineering Manager

Freshworks
06.2024 - Current
  • Primary Product Ownership - Launched Freddy AI Agent Studio which is a platform to create custom AI agent for any business use case. Adapted by 50+ clients in a month period
  • Designed in-house agentic framework enabling LLM integration, tool-calling, search, MCP, and A2A for multi-agent collaboration across Freshworks use cases.
  • Integrated guardrails and security layers for safe and compliant LLM interactions.
  • Implemented semantic search capabilities for features like co-pilot slider, LLM assistant selection, and conversational intent detection.
  • Redesigned information retrieval system to function as both a tool and AI agent within the agentic platform.
  • Built a native assistant platform to power conversational bots, enabling creation of in-house assistants.
  • Developed a QnA bot that learns from external resources and fine-tunes LLMs for domain-specific answering.
  • Enabled gateway endpoints for app/tenant-specific services on top of LLMs, offering unified access to vendor-based LLM APIs.
  • Engineered a rate-limiting system to support metering, quotas, and business-specific usage policies.
  • Established MLOps pipelines to streamline model development and deployment for data science teams.
  • Enhanced operational resilience and platform reliability through systematic Ops improvements.
  • Boosted developer productivity by integrating Cursor as the default development environment (IDE).
  • Team size handling - 14

Engineering Manager

Bigbasket
11.2021 - 06.2024
  • Managing warehouse operations team for all business lines (Standard Delivery, BBDaily, BBNow). Warehouse operation includes receiving skus from suppliers, put into our inhouse structure of racks and bins, picking of order skus and its optimisation for last mile delivery. Execute and manage delivery and with 15 team members
  • Created the warehouse and supply chain structure in house from scratch
  • Revamped the warehouse and inventory receiving, replenishment and picking operations via inhouse system, It helps to increase efficiency for BBNow instant delivery as well increase in revenue by removing third party vendor tools and process and optimizing the order per vehicle strategy
  • Exposed new inhouse warehouse operations system as SaaS offering, it includes making the infra isolated robust and scalable, microservices multi-tenant. It is accessible at https://www.bbmatrix.ai/
  • Scale the backend stack to support 10x increase in business combining BBNow and standard delivery after launching in multiple T4 cities as expansion plan
  • Revamped existing frontend and backend app for managing farmers and its crop management to increase transparency and reflecting it in BB-Fresho store
  • Improved services availability at peak load by introducing proper alert, helm configs, escalation and oncall process

Associate Architect

ZS Associates
09.2018 - 10.2021
  • Designed a new product named Verso for ZS Associates and helped to execute the development and release cycle by leading a team of 8 people.
  • Created ML and MLOps pipeline for scalability for all proprietary algorithms at Organization level for production .Pipeline includes pyspark, Sagemaker, Distributed Tensorflow, alibi for drift and outlier detection, SHAP for explaining
  • Scalable Deep Learning algorithm creation and deployment for engagement of sales rep for multi-country, multi-channel marketing to maximize sales. Scalability is achieved through batch based input sequence processing and map-reduce incorporation in distributed tensorflow on ec2 spot instances. Model training time was reduced from 5hrs to 50min at the same infra cost.
  • Multiple versions of the above model for different products need to be supported. It was done migrating from the current strategy of Sagemaker ec2 instances to Spark cluster of EMR and managing resources efficiently through yarn. This also results in 40% reduction in infra cost
  • Enhanced the genetic algorithm execution time for predicting the sequence of engagement of marketing channels to run in a scalable manner. Improvement of 110x by increasing cost of 6x and making it horizontally scalable. Code level changes include migration from plain python genetic algorithm to pySpark and genetic algorithm's mutations and crossover was bounded inside UDF to run in parallel and efficient way
  • Successfully onboard existing deep learning algorithm training on Sagemaker which was earlier trained on local laptops with smaller dataset due to scalability issues.
  • Multiple POCs related to MLFlow, Metaflow, model training on GPUs, low latency inferencing of ML models through gRPC and nvidia Triton Server were done
  • Troubleshoot and tune the spark jobs (recommendation engine on cosine similarity) memory issue using yarn
  • Designed and created Chatbot using Dialog Flow.
  • Created a recommender system for recommending insights based on user and item-based similarity on mobile App

Tech Lead

Excelsoft Technology
10.2016 - 08.2018
  • Created 3 new modules and redesign some existing modules for Analytics Product Cognowise.
  • Created data pipeline for product to ingest data from Learning Record Store (LRS) to process and store in real time using Apache Storm and its middleware using spring for analytics system of student retention.
  • Created predictive analytics as a service (SaaS) having machine learning based models in spring with apache spark, mllib and multiple brokers.
  • Created an Alert and Notification service with custom processing using Apache Storm.
  • Migrated data from mysql to mongodb and HBase using spark and sqoop. Spark is used for a given time range(historical), sqoop is used for incremental.

Software Engineer

hCentive Technology
11.2015 - 10.2016
  • Development of access control(ACL) on the health exchange agent portal web pages for brokers of different roles
  • Modification in existing batch jobs for renewal of health insurance of government exchanges ( Obamacare) for the upcoming year

Software Engineer

Excelsoft Technology
09.2013 - 10.2015
  • A complete backend codebase designing and development of virtual simulation of MS-Office for online training, along with end to end deployment in Amazon cloud as a SaaS in a team of five people. (Development from scratch).
  • Environment creation for test and performance, creating and configuring machines on AWS and VMware cloud.
  • Developed the script of logstash for log analysis of tomcat logs
  • Automation script of blue-green deployment on production using Jenkins through bash

Software Engineer

Yatra.com
06.2012 - 09.2013
  • A complete frontend to backend designing and development of online e-ticketing for international flight of live website in PDF format including API Integration as well as exposing it as a web service for other internal system.
  • Reduced the render time for Search Flight Page of live website from 3 second to 1 second.(absence of cache) by changing the xslt search pattern of flight details from Amadeus System.
  • A Part of core Back-End Team of Travel and did the API Integration with Amadeus cloud for Special Price handling on festive occasions
  • A complete frontend to backend designing and development of near search city options in International Search on live website.

Education

B-Tech - Computer Science

NIT Jalandhar
Jalandhar, India
05-2012

Skills

    LLMs & Inference:
    vLLM Inference, OpenAI Assistant, experience with multiple LLMs

    Vector DB & Search:
    Elasticsearch, Pinecone

    Cloud & MLOps:
    Azure ML Services, AWS Bedrock, Databricks, MLFlow

    Evaluation & Guardrails:
    Guardrails AI, DeepEval, RAGAs

    Embedding & Reranking:
    BGEM3, MPNetV2, MiniLLM, BGE-Reranker-V2-M3, Qwen3-Reranker-4B

    Automation & Orchestration:
    Netflix Conductor, n8n

    Programming Languages:
    Java, Python, Go, PHP, SQL, Shell Scripting

    Web & App Development:
    Spring Boot, J2EE (JSP, Servlets), Spring MVC, Spring Data, Hibernate, Thymeleaf, Laravel, Spring React, WebSocket, Swagger, Zuul, Hystrix, Actuator

    Databases:
    Oracle, MySQL, PostgreSQL, Cassandra, MongoDB

    Monitoring & Observability:
    Zabbix, ELK Stack, New Relic, Datadog

    Machine Learning & Data Science:
    scikit-learn, MLlib, Teapot, Orange, Pandas, Matplotlib, Jupyter

    Deep Learning:
    Keras, PyTorch

    Big Data & Caching:
    Apache Spark, Kafka, Storm, Kylin, HDFS, Memcached, Redis, Logstash

    ETL Tools:
    Pentaho Data Integration

    Security Tools:
    Burp Suite, SQLMap, NMap

    Cloud Platforms:
    AWS: IAM (User/Admin), EC2, S3, VPC, ELB, RDS, Lambda, API Gateway, CloudFront, R5
    Azure: Azure ML Services

Timeline

Engineering Manager

Freshworks
06.2024 - Current

Engineering Manager

Bigbasket
11.2021 - 06.2024

Associate Architect

ZS Associates
09.2018 - 10.2021

Tech Lead

Excelsoft Technology
10.2016 - 08.2018

Software Engineer

hCentive Technology
11.2015 - 10.2016

Software Engineer

Excelsoft Technology
09.2013 - 10.2015

Software Engineer

Yatra.com
06.2012 - 09.2013

B-Tech - Computer Science

NIT Jalandhar

Similar Profiles

CREATE PROFILE
Ravi Ranjan