Salesforce / MuleSoft · 2025 to Present
Governed LLM gateway
A controlled layer between enterprise applications and multiple model providers, so access, routing and policy are decided in one place instead of separately in every application.
Hi, I’m Sid. Siddhartha Jagadesh.
Senior Software Engineer · Salesforce / MuleSoft AI
I build the platform layer behind enterprise AI: governed LLM access, agent orchestration, and reliable distributed systems.
Get in touchSalesforce / MuleSoft · Microsoft · ServiceNow · Zoho
- LLM Gateways
- Agent Orchestration
- AI Governance
- Distributed Systems
- MCP · A2A Policies
- Identity & Quota
Projects
Selected work
Three case studies, each built around a real engineering problem.
Salesforce / MuleSoft · 2025 to Present
Multi-agent orchestration
Configurable coordination of several specialised agents inside a governed workflow, instead of routing every task through one general-purpose agent.
Microsoft · 2022 to 2024
Near-real-time privacy pipeline
A scrubbing mechanism for support data that met privacy obligations without giving up the low latency the data was valuable for.
Career
Experience
2025 to Present
Salesforce / MuleSoftSenior Software Engineer, MuleSoft AI
Platform work for MuleSoft's AI products: agent orchestration, the gateway in front of the model providers, and the governance that has to hold once real customers point traffic at it.
2022 to 2024
MicrosoftSoftware Developer
Data movement and privacy-aware processing for internal support systems, where privacy rules and latency targets pulled in opposite directions.
2020 to 2022
ServiceNowSoftware Developer IC2
Workflow tooling aimed at people who are not engineers, and a long-running effort to hold the product to real accessibility standards.
2018 to 2020
Zoho CorporationBack-End Developer
Backend work on Zoho Notebook, mostly around making transfers reliable and downloads fast, where reliability stopped being just a word in a design doc.
About
About me
For about eight years I have built backend platforms, enterprise workflow systems and, more recently, the infrastructure that production AI runs on. Right now I am on the MuleSoft AI team at Salesforce, working on multi-agent orchestration, the policies that govern how agents reach tools, and the gateway in front of the model providers. What I like most is the quiet part: getting something safe enough that a colleague can pick it up without asking me first.
Expertise
What I do
LLM Gateways
One governed layer between enterprise applications and many model providers, so access, routing and cost are decided once instead of separately in every app.
Agent Orchestration
Multi-agent workflows where specialised agents coordinate safely under policy, using MCP and agent-to-agent communication.
AI Governance
Identity, delegated authority, quota and cost enforced in front of inference, so revocation is a control rather than a receipt.
Distributed Systems
Data pipelines under privacy constraints and the unglamorous reliability and performance work that keeps a platform trustworthy at scale.
Platform Engineering
Making the useful part of a system reusable while keeping the dangerous part out of reach.
Writing
Writing and the System Design course
System Design course
22 lessons published
Currently in Foundations: Why one machine stops being enough, and the handful of ideas every distributed system is built from.