[{"content":"Welcome to my blog. I write about Systems Engineering, ML Engineering, GenAI, Distributed Systems, and things I encounter building production AI systems.\nExpect posts on LLMs, RAG, agentic systems, MLOps, Spark, and system design mostly things I\u0026rsquo;ve built or learned in my journey.\nThanks for stopping by.\n","permalink":"https://sriharan.pages.dev/blog/hello-world/","summary":"First post — what this blog is about and what to expect.","title":"Hello, World"},{"content":"\u0026mdash; title: \u0026ldquo;Project One\u0026rdquo; date: 2024-01-01 tags: [\u0026ldquo;Go\u0026rdquo;, \u0026ldquo;PostgreSQL\u0026rdquo;, \u0026ldquo;Docker\u0026rdquo;] summary: \u0026ldquo;A short one-line description of what this project does.\u0026rdquo; \u0026mdash; ## Overview What the project does, the problem it solves, and who it\u0026rsquo;s for. ## Tech Stack - Backend: Go - Database: PostgreSQL - Infrastructure: Docker, GitHub Actions ## Links - GitHub - Live Demo ","permalink":"https://sriharan.pages.dev/projects/project-one/","summary":"\u003ch1 id=\"heading\"\u003e\u0026mdash;\u003c/h1\u003e\n\u003ch1 id=\"title-project-one\"\u003etitle: \u0026ldquo;Project One\u0026rdquo;\u003c/h1\u003e\n\u003ch1 id=\"date-2024-01-01\"\u003edate: 2024-01-01\u003c/h1\u003e\n\u003ch1 id=\"tags-go-postgresql-docker\"\u003etags: [\u0026ldquo;Go\u0026rdquo;, \u0026ldquo;PostgreSQL\u0026rdquo;, \u0026ldquo;Docker\u0026rdquo;]\u003c/h1\u003e\n\u003ch1 id=\"summary-a-short-one-line-description-of-what-this-project-does\"\u003esummary: \u0026ldquo;A short one-line description of what this project does.\u0026rdquo;\u003c/h1\u003e\n\u003ch1 id=\"heading-1\"\u003e\u0026mdash;\u003c/h1\u003e\n\u003ch1 id=\"-overview\"\u003e## Overview\u003c/h1\u003e\n\u003ch1 id=\"what-the-project-does-the-problem-it-solves-and-who-its-for\"\u003eWhat the project does, the problem it solves, and who it\u0026rsquo;s for.\u003c/h1\u003e\n\u003ch1 id=\"-tech-stack\"\u003e## Tech Stack\u003c/h1\u003e\n\u003ch1 id=\"--backend-go\"\u003e- \u003cstrong\u003eBackend:\u003c/strong\u003e Go\u003c/h1\u003e\n\u003ch1 id=\"--database-postgresql\"\u003e- \u003cstrong\u003eDatabase:\u003c/strong\u003e PostgreSQL\u003c/h1\u003e\n\u003ch1 id=\"--infrastructure-docker-github-actions\"\u003e- \u003cstrong\u003eInfrastructure:\u003c/strong\u003e Docker, GitHub Actions\u003c/h1\u003e\n\u003ch1 id=\"-links\"\u003e## Links\u003c/h1\u003e\n\u003ch1 id=\"--github\"\u003e- \u003ca href=\"https://github.com/sriharan16/project-one\"\u003eGitHub\u003c/a\u003e\u003c/h1\u003e\n\u003ch1 id=\"--live-demo\"\u003e- \u003ca href=\"https://example.com\"\u003eLive Demo\u003c/a\u003e\u003c/h1\u003e","title":""},{"content":"\u0026mdash; title: \u0026ldquo;Project Two\u0026rdquo; date: 2023-06-01 tags: [\u0026ldquo;Python\u0026rdquo;, \u0026ldquo;React\u0026rdquo;, \u0026ldquo;AWS\u0026rdquo;] summary: \u0026ldquo;Another short description of this project.\u0026rdquo; \u0026mdash; ## Overview What the project does and why you built it. ## Tech Stack - Frontend: React, TailwindCSS - Backend: Python / FastAPI - Hosting: AWS EC2 ## Links - GitHub ","permalink":"https://sriharan.pages.dev/projects/project-two/","summary":"\u003ch1 id=\"heading\"\u003e\u0026mdash;\u003c/h1\u003e\n\u003ch1 id=\"title-project-two\"\u003etitle: \u0026ldquo;Project Two\u0026rdquo;\u003c/h1\u003e\n\u003ch1 id=\"date-2023-06-01\"\u003edate: 2023-06-01\u003c/h1\u003e\n\u003ch1 id=\"tags-python-react-aws\"\u003etags: [\u0026ldquo;Python\u0026rdquo;, \u0026ldquo;React\u0026rdquo;, \u0026ldquo;AWS\u0026rdquo;]\u003c/h1\u003e\n\u003ch1 id=\"summary-another-short-description-of-this-project\"\u003esummary: \u0026ldquo;Another short description of this project.\u0026rdquo;\u003c/h1\u003e\n\u003ch1 id=\"heading-1\"\u003e\u0026mdash;\u003c/h1\u003e\n\u003ch1 id=\"-overview\"\u003e## Overview\u003c/h1\u003e\n\u003ch1 id=\"what-the-project-does-and-why-you-built-it\"\u003eWhat the project does and why you built it.\u003c/h1\u003e\n\u003ch1 id=\"-tech-stack\"\u003e## Tech Stack\u003c/h1\u003e\n\u003ch1 id=\"--frontend-react-tailwindcss\"\u003e- \u003cstrong\u003eFrontend:\u003c/strong\u003e React, TailwindCSS\u003c/h1\u003e\n\u003ch1 id=\"--backend-python--fastapi\"\u003e- \u003cstrong\u003eBackend:\u003c/strong\u003e Python / FastAPI\u003c/h1\u003e\n\u003ch1 id=\"--hosting-aws-ec2\"\u003e- \u003cstrong\u003eHosting:\u003c/strong\u003e AWS EC2\u003c/h1\u003e\n\u003ch1 id=\"-links\"\u003e## Links\u003c/h1\u003e\n\u003ch1 id=\"--github\"\u003e- \u003ca href=\"https://github.com/sriharan16/project-two\"\u003eGitHub\u003c/a\u003e\u003c/h1\u003e","title":""},{"content":"Hi, I\u0026rsquo;m Sriharan Manogaran — a Lead Software Engineer based in Chennai, India, specialising in Machine Learning, NLP, GenAI, Agentic Systems and Distributed Systems.\nI have 7+ years of experience building production-grade ML systems, spanning traditional NLP, statistical ML, and modern GenAI. Deep expertise across the full ML spectrum: from classical anomaly detection, distributional profiling, and embedding-based classifiers to LLM-powered applications, RAG pipelines, and agentic systems. Strong distributed systems foundation (Apache Spark, Kafka, SQS) and hands-on cloud infrastructure experience (AWS, Kubernetes).\nCo-architect of Freshworks\u0026rsquo; Freddy AI Insights platform, processing 200M+ ML evaluations daily at 99.99% SLA compliance. Currently driving the GenAI evaluation framework for all Copilot AI features across Freshworks products.\nProven track record of leading high-performing ML teams, filing patents, and delivering systems that scale from prototype to millions of users.\nGet in touch · Read my blog\n","permalink":"https://sriharan.pages.dev/about/","summary":"About Sriharan Manogaran","title":"About"},{"content":" GitHub LinkedIn Based in Chennai, India.\n","permalink":"https://sriharan.pages.dev/contact/","summary":"Get in touch","title":"Contact"},{"content":"📄 Download Resume (PDF)\nLead Software Engineer – Machine Learning Freshworks, Chennai, India · Apr 2023 – Present\nFreddy AI Insights — Key Co-Architect\nCo-architected a distributed intelligence engine surfacing anomalies, trends, and root cause analysis for enterprise customers, processing ~32M data-generation queries and ~200M ML evaluations daily across tens of thousands of tenants. Led AI/ML layer: statistical profiling algorithms (distributional skew, monotonicity detection, longest-contiguous-subsequence analysis, change-point detection) executed as in-memory Spark batch jobs within a strict 1-hour SLA. Designed a multi-stage async architecture (SQS + Kafka + Spark Streaming + Spark Batch) achieving 99.99% SLA compliance and ~5% of legacy pipeline cost while processing 10× the data volume. Built a config-driven ML pipeline (YAML → dynamic Databricks Spark DAG) allowing new products to onboard new insight types in days. Coordinated delivery across 6 cross-functional teams; presented architecture at the Freshworks Architects\u0026rsquo; Forum and co-authored the Freshworks Engineering Blog post (March 2026). Conversational Analytics – Agentic AI\nBuilt a natural language to chart/graph system for the Freshworks Analytics Platform, serving 17K+ requests across 4K+ accounts in production. Designed a fully custom agentic orchestration system (predating LangChain/LangGraph) with custom tool routing, state management, and multi-turn conversation handling. Implemented RAG pipelines grounding the system in product-specific data schema and metric definitions. GenAI Evaluation Framework — Current Initiative\nArchitecting a standardised evaluation pipeline for all Copilot GenAI features, unifying the AI Agent Platform with Databricks/MLflow via Arize Phoenix. Designed a Medallion data strategy (Bronze → Silver → Gold Delta tables) normalising live traces and offline simulation data for LLM-as-a-Judge evaluation. Enabled offline experimentation using curated Golden Datasets against sandboxed test agents. MLOps \u0026amp; Infrastructure\nManaging AWS infrastructure (VPC, Kubernetes, RDS, SQS, S3, EFS, Lambda) for the Neo Analytics AIML team. Optimised pipeline costs by ~24% through Karpenter autoscaling, Nitro instance migration, and VPC endpoint optimisations. Managing Databricks workspaces and Unity Catalog across 5 regions. Senior Software Engineer – Machine Learning Freshworks, Chennai, India · Oct 2021 – Mar 2023\nLed a team of 4 to design and deliver a multi-product, multi-tenant custom intent detection system handling 1M+ requests/day from 10K+ active bots in production. Architected the full E2E system: FastAPI + Celery microservices, real-time inference, and active learning pipeline backed by MongoDB, Redis, S3, and Elasticsearch. Used LaBSE multilingual sentence embeddings for cross-language intent detection without per-language model variants. Built Freshworks\u0026rsquo; first MLOps platform on Databricks covering experiment tracking, feature store, and model registry; integrated KServe for production model serving. Coordinated with 8 cross-functional teams for delivery and 3 additional product teams for integration. Software Engineer – Machine Learning Freshworks, Chennai, India · Apr 2020 – Sep 2021\nExtended the core bot platform to Freshchat and Freshservice, scaling to 60K+ customers and 200K+ bots. Fine-tuned a BERT model for IT Support Bot Service Item Suggester on Freshservice, deployed via TensorFlow Serving. Developed a V2 Solution Article Suggester using MUSE embeddings with improved accuracy and cross-language relevance. Graduate Trainee – Software Engineering Freshworks, Chennai, India · Jun 2019 – Mar 2020\nBuilt the core multi-tenant model training and data sync pipeline for Freshdesk bots, serving 42K+ customers and 90K+ bots. Stack: Java, Spring Boot, Kafka, MySQL, Redis. Education Bachelor of Engineering – Computer Science Sathyabama Institute of Science \u0026amp; Technology, Chennai · 2015 – 2019\n","permalink":"https://sriharan.pages.dev/experience/","summary":"Work experience and career history","title":"Experience"},{"content":"Programming Languages Python · Java · SQL\nML \u0026amp; AI NLP · Intent Detection · Multilingual Embeddings · Anomaly Detection · Statistical Profiling · Model Fine-tuning \u0026amp; Quantization\nLLMs \u0026amp; GenAI RAG · LLM Orchestration · LangChain · LangGraph · Agentic Systems · Prompt Engineering · LLM-as-a-Judge · GenAI Evaluation Framework\nMLOps Databricks · MLflow · KServe · Arize Phoenix · Model Serving\nFrameworks FastAPI · Spring Boot · Apache Spark (Streaming \u0026amp; Batch) · Celery\nSystem Design Distributed Systems · Microservices · Event-Driven Architecture · Scalability · Multi Tenant Systems\nDatabases MySQL · MongoDB · Redis · Elasticsearch · PostgreSQL · Snowflake · E6\nInfrastructure \u0026amp; Cloud AWS (VPC, Kubernetes, SQS, Kafka, Lambda, RDS, S3, EFS, etc) · CI/CD (Jenkins, AWS CodePipeline, GitHub Actions)\n","permalink":"https://sriharan.pages.dev/skills/","summary":"Technical skills and tools","title":"Skills"}]