Hello there — I'm

Saravanamuthu S

Senior Software Engineer · AI Platform & Backend Engineer

I build production-grade backend systems, autonomous multi-agent AI platforms and multi-cloud deployment tooling used by thousands of people — from real-time distributed architecture and self-improving learning layers down to squeezing every last millisecond out of high-throughput Go services.

4+ years shipping
production systems
1,400+ skills integrated into
the Super Agent platform
~30% less RAM under
peak production load
750+ components in the
AIA workflow catalog
01

About

I'm a software engineer who likes owning the hard, unglamorous middle of a product — the part between a clever idea and something thousands of people can actually rely on. My home turf is autonomous multi-agent systems, LLM agent orchestration, context engineering and high-throughput Go services.

Over the last four years I've taken critical systems end-to-end — from the first architecture sketch through to performance tuning in production, and even a self-improving learning layer that makes the platform get better with every run — while working shoulder-to-shoulder with product and engineering to ship things that matter.

Portrait photo of Saravanamuthu S
yep, that's me
02

Experience

Senior Software Engineer

Adya.ai

Aug 2023 — Present

Autonomous Multi-Agent Platform (SAI)

  • Architected the supervisor core of SAI, an autonomous multi-agent delivery system that turns a plain-language request into delivered artifacts — classifying intent, generating multi-phase plans, delegating to specialist agents, and running independent steps in parallel through a DAG engine with dependency resolution, retries and cascade-failure handling.
  • Re-architected the skill system into a central skill registry — metadata indexed in a vector database, raw definitions in MongoDB — equipping 1,400+ skills on demand at runtime and auto-installing new capabilities from an online marketplace when no local match exists.
  • Engineered a 3-layer context-management system (Auto Compact) — cross-request, per-call and per-tool-call compaction — so long agent-building sessions run unbounded without hitting LLM token limits.
  • Built HAA (Human Assistant Agent) on a per-workspace VM context layer that stores and retrieves workflow context, memory and session summaries — letting the assistant auto-answer user questions on their behalf.
  • Added human-in-the-loop control (plan approve / modify / reject, mid-run questions) and multi-channel engagement — WhatsApp, Email, In-App and Web Push — so users can answer, check status and steer long runs from anywhere.

AI Workflow Automation (AIA)

  • Re-architected the natural-language-to-workflow builder into a master-LLM recursive tool loop that orchestrates specialist sub-agents (requirement gathering, component prediction, flow connection, validation & repair), grounded in a 750+ component catalog (including MCPs) via vector retrieval.
  • Bootstrapped the knowledge base by running real use-cases through AIA's own synthesis engine to generate ~2,000 domain-segmented reference workflows, fed back as grounding data to strengthen the component ontology, retrieval and cold-start learning.
  • Streamed every node and edge live to the canvas on create and update paths, with structural validation and one-shot automated repair of malformed flows.

Self-Improving Learning Layer (ESLL)

  • The platform learns from its own results and gets better with every build. Architected ESLL, a self-improving, event-sourced learning layer for generative AI: it observes each decision and its context, extracts durable knowledge from behavioural telemetry, injects that knowledge into future decisions under a token budget, and attributes outcomes back to the knowledge that shaped them — promoting what works, demoting what doesn't, with no gradient training.
  • Deployed ESLL on the AIA builder to improve workflow synthesis — using materialized projections for credit assignment and demand-signal extraction to surface capability gaps as a product-roadmap input.

Backend, Data & Platform Engineering

  • Designed a no-code ETL platform across major databases, cloud storage and SaaS sources, then evolved it into a fully agentic data pipeline driven by natural-language conversation.
  • Built real-time collaboration and streaming with WebSockets and Server-Sent Events for live concurrent editing and low-latency updates.
  • Cut ~30% RAM under peak load through targeted indexing, Redis caching and MongoDB connection-pool tuning; handled burst traffic with Go routines and channels at stable latency.
  • Integrated multiple MCP servers and extensible components for modular, configurable agent workflows at scale.

Cloud, Infrastructure & Leadership

  • Architected Cloud Studio, a unified PaaS / SaaS deployment platform for AI agents; managed multi-cloud infrastructure hands-on — VMs and AKS on Azure, Compute VMs on GCP, Bedrock LLM access on AWS — with Azure AI Foundry for model and key management.
  • Maintained Dockerised service pipelines, Jenkins deployments and Nginx configuration for consistent environments.
  • Mentored engineers and drove architectural decisions; represented Adya.ai at launch events and workshops, and served as Lead Jury at the SECE hackathon.

Software Engineer Intern

Eunimart

Aug 2022 — Aug 2023

Backend Engineering — ONDC & E-Commerce

  • Engineered backend services for a centralised e-commerce platform fully compliant with ONDC protocol standards using Go and Node.js.
  • Built and enhanced the ONEST platform — a course provider–seeker marketplace and a job provider–seeker marketplace on one unified backend.
  • Developed a Reconciliation Service Provider (RSP) under ONDC to automate transaction reconciliation and settlement.
  • Integrated banking partners including HSBC, IDFC and NPCI for secure, automated reconciliation pipelines.
  • Connected marketplaces, webstores and logistics providers for omnichannel seller operations — strong end-to-end ownership of production backend.
03

Toolkit

Languages

  • Go (Golang)
  • Node.js
  • JavaScript
  • Python (working knowledge)

Backend

  • REST API Design
  • Microservices
  • WebSockets
  • Server-Sent Events
  • Kafka

AI / LLMs

  • Agentic AI
  • Multi-Agent Orchestration
  • LLM Integration
  • Model Context Protocol
  • Context Engineering
  • RAG / Vector Retrieval
  • Self-Improving Learning Systems
  • Browser-Use

Data

  • MongoDB
  • Redis
  • PostgreSQL
  • Vector DB (Milvus / Zilliz)
  • ETL Pipelines
  • Connection Pool Optimization

Cloud & DevOps

  • Azure VM
  • Azure AKS
  • Azure AI Foundry
  • GCP Compute
  • AWS Bedrock
  • Docker
  • Jenkins
  • Nginx
  • PaaS / SaaS

Concepts

  • Distributed Systems
  • Real-Time Architectures
  • System Design
  • Performance
  • Concurrency
  • DAG Orchestration
  • Event Sourcing
04

Education

B.E. — Information Science & Engineering

Bannari Amman Institute of Technology, Sathyamangalam

Class of 2023
05

Beyond the terminal

Open to interesting problems

Let's build something
that holds up.

Backend architecture, agentic AI, real-time systems — if it needs to be fast, reliable and a little bit clever, I'd love to hear about it.