AI Solutions Architect · LLM Engineer · Founder

Balaji Hariharan

I build production AI agent systems that enterprises trust

From multi-agent orchestration and LLM gateways to governance frameworks and MCP protocol servers — I design, build, and ship the complex AI infrastructure that moves agentic AI from prototype to production.

terminal

About

I'm an AI Solutions Architect and LLM Infrastructure Engineer who builds the systems that make agentic AI work in production — not demos, not wrappers, but the governance, security, cost controls, and orchestration layers that enterprises need before trusting autonomous agents with real workflows.

As the founder of ShackleAI, I designed and built an 11-microservice agent platform from scratch: an LLM gateway with multi-provider routing and PII scrubbing, a credential vault with AES-256 encryption and auto-rotation, RBAC+ABAC governance with kill-switches, and an orchestrator that decomposes natural language into executable multi-agent pipelines using CrewAI and OpenClaw.

My open-source contributions include an MCP memory server (1,440+ weekly npm downloads) and a Python async agent framework on PyPI with 2,000+ tests at 97% coverage, per-call cost tracking across 100+ LLM providers, and 37 built-in tools.

I developed a rapid AI-accelerated development methodology — automated GitHub issue management, AI-driven sprint execution, and a 17-agent Claude Code ecosystem that ships production code at lightning speed: 18 iterations in 3 days, 252 commits across the platform in 11 active days, 7 PyPI releases. This isn't just building AI — it's using AI to build AI, faster than any traditional team.

0+
Commits Shipped
0+
Tests Passing
0%
Test Coverage
0+
Weekly npm Downloads
0
CI/CD Runs
0
Issues Closed

18+ Years Before AI Agents

From RPA to AI — I led the first wave of enterprise automation as Managing Director at Softomotive (acquired by Microsoft, became Power Automate). Now I'm building the second wave: autonomous AI agents with governance, security, and enterprise trust built in.

Managing Director, APAC
Softomotive
Acquired by Microsoft → became Power Automate
Principal Engineer
Nagarro
Enterprise application modernization
Service Delivery Lead
FIS
Enterprise automation for BFSI production systems
SAP Technology Consultant
Deloitte
Enterprise systems & process automation
RPA & Enterprise AutomationAI Agent Architecture

Enterprise Clients

MicrosoftWalmartFlipkartAxis BankNedbankSanofiDeloitteCapgemini

Domain Expertise

BFSI & Core BankingRetail & E-CommerceOil & GasPharma & LogisticsAutomobileEnterprise Automation

Projects

Production systems I have built — from AI agent platforms to open-source developer tools.

ShackleAI Platform

142PRs Shipped

The Operating System for AI Agents — 11 microservices, 142 API routes, 367 issues closed, 142 PRs merged, 1,836 CI/CD workflow runs. LLM Gateway, Credential Vault, Agent Governance, Orchestrator, and MCP-native tool infrastructure.

Next.jsTypeScriptPostgreSQLpgvectorRedisDockerMCP

@shackleai/memory-mcp

1,440+Weekly Downloads

Open-source persistent memory for AI coding tools. The first MCP-native memory server with semantic search, offline embeddings, and zero-config setup. Used by Claude Code, Cursor, and Windsurf developers worldwide.

TypeScriptMCP ProtocolEmbeddingssqlite-vecTransformers.js

ShackleAI Agent Framework (PyPI)

2,000+Tests at 97% Coverage

Enterprise-grade async-first Python agent orchestration on PyPI. 37 built-in tools, per-call cost tracking across 100+ LLM providers, PyArmor-protected releases. 2,000+ tests at 97% coverage across 117 test files.

Python 3.12AsyncIOLiteLLMPydantic v2FastAPIOpenTelemetry

WhatsApp AI Chat Platform

10Phases Shipped

RAG-powered WhatsApp AI assistant for small businesses. Semantic search over business catalogs and FAQs, automated payment flows via Razorpay, action token parsing for escalation and order management. 10 development phases completed.

Node.jsExpressNext.jsPostgreSQLpgvectorOpenAIWhatsApp API

ShackleGuard

6Attack Categories

"Lighthouse for AI Agents" — AI agent security and red-team testing platform. Automated prompt injection detection, jailbreak testing, PII leakage scanning, hallucination measurement, and EU AI Act compliance reporting. Currently in design phase.

AI SecurityRed TeamingOWASP LLM Top 10Prompt InjectionCompliance

Errakaaram

563Commits Shipped

Production e-commerce platform serving real customers. 29 data models, 124+ pages, device-adaptive routing, Razorpay payments, AWS S3/CloudFront CDN, 563 commits across frontend and backend, automated CI/CD deployment.

Next.jsExpressMongoDBRedisAWSRazorpay

Skills & Expertise

Deep specialization in agentic AI systems — from architecture and LLM engineering to the operational layer that makes agents production-ready.

Agent Architecture

Multi-Agent OrchestrationMCP Protocol (built server from scratch)CrewAI / OpenClaw IntegrationTool Calling & Function ExecutionAgent Governance (RBAC + ABAC)Pipeline Decomposition

LLM Engineering

Multi-Provider Routing (OpenAI, Anthropic, Azure, Bedrock)RAG PipelinesEmbedding Models (OpenAI, MiniLM-L6-v2)Vector Search (pgvector, sqlite-vec)LiteLLM (100+ providers)Prompt Engineering & Policy Enforcement

AI Operational Layer

LLM Gateway (budget, metering, fallback)PII Detection & ScrubbingPer-Call Cost TrackingCredential Vault (AES-256, rotation, audit)Agent Observability (OpenTelemetry)Kill-Switch & Approval Workflows

AI-Accelerated Development

17-Agent Claude Code EcosystemAutomated GitHub Issue ManagementAI-Driven Sprint ExecutionRapid Iteration (18 iterations in 3 days)1,836 Automated CI/CD Runs367 Issues Resolved via Agents

Platform Engineering

PostgreSQL + pgvectorRedisDocker & Container OrchestrationAWS (S3, SES, Route 53, Lightsail)CI/CD (GitHub Actions)Caddy (Reverse Proxy, Auto-SSL)

Languages & Frameworks

TypeScript / PythonNext.js / React 19FastAPI / ExpressPydantic v2 / ZodVitest / Playwright / pytestAsync-First Architecture

My 17-Agent AI Development Team

Custom-built Claude Code agents I designed and operate — each specializes in a domain, collectively shipping production code 24/7

O
Platform Engineer
Backend services, API routes, core logic
O
Frontend Engineer
Next.js, React, dashboard UI
O
Database Architect
PostgreSQL, pgvector, migrations
O
Security Engineer
Auth, RBAC, encryption, OWASP
O
Code Reviewer
Quality, patterns, architecture review
O
Issue Architect
Sprint planning, gap analysis, GitHub ops
O
SEO Engineer
Technical SEO, meta tags, JSON-LD
S
API Designer
REST/MCP protocol, OpenAPI specs
S
DevOps Engineer
Docker, CI/CD, VPS, deployment
S
Test Engineer
Vitest, Playwright, E2E, security tests
S
QA Orchestrator
Quality gates, lint/build/test validation
S
Docs Writer
API docs, user guides, runbooks
S
Release Manager
Versioning, changelogs, rollbacks
S
Business Analyst
Market research, pricing, positioning
S
Content Strategist
SEO keywords, content planning
S
Ecosystem Auditor
Health checks, velocity tracking
S
UX Auditor
Accessibility, responsive, usability

Work With Me

Whether you need an AI architect for your enterprise, a technical co-builder for your startup, or a specialist for a complex agent project — here's how I can help.

Enterprise & Corporate

AI agent platform architecture, LLM gateway design, governance frameworks, and production deployment strategy for enterprise teams.

CTOs, VPs of Engineering, AI Directors

AI Startups & Founders

Technical co-building, architecture review, and hands-on engineering for startups building agentic AI products — from zero to production.

AI Founders, Technical Co-founders

Complex AI Projects

Multi-agent orchestration, MCP server development, LLM pipeline engineering, RAG systems, and custom agent frameworks as a freelance specialist.

Teams needing senior AI engineering

Rapid AI Development

I use an AI-accelerated iteration methodology — automated GitHub issue management, AI-driven sprint execution, and a 17-agent ecosystem that ships production code at lightning speed. 18 iterations in 3 days, 252 commits in 11 days.

Teams that need to move fast

Training & Workshops

Hands-on workshops on building production agent systems, MCP protocol, LLM infrastructure patterns, and AI-native development workflows.

Engineering teams, Bootcamps, Conferences

Advisory & Consulting

AI strategy consulting, technology due diligence, agent architecture reviews, and vendor-neutral guidance on LLM infrastructure decisions.

Executives, Investors, Product Leaders

Full-Time Roles

Open to Staff/Principal AI Engineer, AI Platform Architect, or Head of AI Infrastructure roles at companies building serious agent systems.

Recruiters, Hiring Managers

Open Source

Tools I have built and released for the developer community.

@shackleai/memory-mcp

v0.5.2

Persistent memory for AI coding tools. The first MCP-native memory server.

... weekly downloads
npm install @shackleai/memory-mcp
11 MCP toolsSemantic searchOffline embeddingsZero config

Journey

Key milestones in building AI infrastructure.

2025

Founded ShackleAI

Started building the Operating System for AI Agents

2025

Launched Memory MCP

Published @shackleai/memory-mcp on npm — now 1,440+ weekly downloads globally

2025

Built Agent Framework

Python async-first orchestration on PyPI — 2,000+ tests, 97% coverage, 37 built-in tools

2025

Shipped Chat Platform

WhatsApp AI assistant with RAG — 10 development phases completed

2026

V2 Platform Pivot

Integrated OpenClaw + CrewAI for browser automation and multi-agent workflows

2026

AI-Accelerated Development

Built 17-agent ecosystem — 928+ commits, 142 PRs merged, 1,836 CI/CD runs, 367 issues closed

Let's Talk

Whether you're hiring for an AI infrastructure role, need a freelance specialist for a complex agent project, looking for a technical co-builder for your AI startup, or want to bring hands-on AI workshops to your team — I'd love to hear from you.

contact@balajihariharan.com