0%

$ init jeet.soni

› loading agents............ok

› rag pipeline.............ok

› guardrails...............ok

› deploying portfolio......ok

Ahmedabad, India

AI ENGINEER · AGENTIC SYSTEMS · RAG · FULL-STACK

Jeet Soni

I build AI agents that survive production, and the platforms they run on.

GitHubLinkedInYouTube
Scroll
AI Agents✳RAG Pipelines✳MCP✳Next.js✳Multi-Agent Orchestration✳TypeScript✳Vector Search✳Guardrails✳Generative UI✳Clean Architecture✳LLM Observability✳Python✳AI Agents✳RAG Pipelines✳MCP✳Next.js✳Multi-Agent Orchestration✳TypeScript✳Vector Search✳Guardrails✳Generative UI✳Clean Architecture✳LLM Observability✳Python✳
AI Agents✳RAG Pipelines✳MCP✳Next.js✳Multi-Agent Orchestration✳TypeScript✳Vector Search✳Guardrails✳Generative UI✳Clean Architecture✳LLM Observability✳Python✳AI Agents✳RAG Pipelines✳MCP✳Next.js✳Multi-Agent Orchestration✳TypeScript✳Vector Search✳Guardrails✳Generative UI✳Clean Architecture✳LLM Observability✳Python✳

0+

Years of engineering

0+

Production AI agents shipped

0

LLM agents in one pipeline

0/1000

Claude Certified Architect

01Who

AI Engineer with 5+ years across full-stack and applied-AI development, now leading both the build of an enterprise LLM agent platform and its delivery to clients who bet real workflows on it.

As founding engineer of AgentOS at AvestaLabs, I shaped an agent orchestration platform from whiteboard to production: context engineering, RAG pipelines, vector-backed agent memory, MCP client and server, custom tools, guardrails.

I sit on both sides of the table: architecting the platform, then embedding with enterprise clients to map their workflows and ship agents that hold up when real users arrive. Ten-plus production GenAI agents across finance, legal, media, real estate, e-commerce and travel.

Everything runs on a full-stack spine of Next.js, Node.js, TypeScript and Python, with an architect's bias for ports & adapters, DDD, and systems that can swap their LLM without rewriting their soul.

Demos are easy.
Production is the product.

Working philosophy

02Trajectory

Dec 2024 → Present

AvestaLabs

AI Product Engineer & Team Lead

Avesta HQ's AI division

  • Founding engineer of AgentOS, an enterprise suite to design, deploy, evaluate and monitor AI agents; lead the core engineering team.
  • Architected Efficia, the agent orchestration product: context engineering, RAG, vector-backed agent memory, MCP client/server, custom tools framework, guardrails.
  • Embedded technical lead on enterprise engagements, with 10+ production agents live across finance, legal, media, real estate, e-commerce and travel.
  • Shipped OnlyFacts: climate questions answered as real-time generative UI. India Avenue: a customer-facing fund-data agent. Legal automation: lawyer-ready contracts drafted in 3–5 minutes.
AgentOSEfficiaMCPRAGGuardrailsTeam Lead

May 2023 → Dec 2024

Avesta HQ

Software Engineer

Ahmedabad, India

  • Spearheaded the complete rebranding and feature expansion of view.com.au, a major Australian real-estate portal, on Next.js, Node.js and PostgreSQL.
  • Led end-to-end delivery of product features, working directly with PMs and clients on requirements.
  • Designed implementation architecture and mentored the team on Next.js best practices and design patterns.
Next.jsNode.jsPostgreSQLArchitecture

Jan 2021 → May 2023

Space-O Technologies

MERN Stack Developer

Ahmedabad, India

  • Built and maintained MERN applications: analytical dashboards, CRM web apps, delivery platforms.
  • Integrated secure payment gateways (Stripe, TYRO) across multiple web applications.
  • Star Performer of the Month.
ReactNode.jsMongoDBStripe

Dec 2019 → Sep 2020

9Brainz · TRUESYS

MEAN / Web Developer

Early career

  • Engineered MEAN-stack web APIs and real-time Angular applications; AWS API Gateway, Lambda, DynamoDB for cloud-native projects, growing from intern to live-project delivery.
AngularAWSNode.js
03Selected Builds

Swipe the cards →

LIVE
01

KalpanaAI

AI Video Generation Platform · Founder

Type a topic, get a fully narrated, animated, rendered MP4. ~17 specialized LLM agents orchestrated through one automated pipeline: scripting, voiceover, scene direction, code generation, metadata.

  • 16-stage fault-tolerant pipeline on BullMQ/Redis with per-stage retries and SSE progress a reconnecting browser never loses
  • An agentic loop where an LLM writes React/Remotion animation code that is compile-validated, runtime-checked, auto-repaired and then rendered with word-timestamped voiceover
  • Provider abstraction that hot-swaps LLM, TTS and transcription by config; self-hosted GPU TTS sidecar kills the dominant per-video cost
  • Dogfooded daily: every SynapByte video is generated end-to-end by the platform
TypeScriptNext.js 15Express 5BullMQRemotionCloudflare R2Langfuse
video-ai-web-production.up.railway.app↗
kalpana.ai/studio
KalpanaAI studio: turn any idea into a finished video
LIVE
02

DICOM Viewer

AI-Assisted Radiology Platform

A mobile-first web DICOM viewer for radiologists (CT, MR, X-ray, ultrasound) with an agentic AI reader that autonomously drives the viewer itself.

  • Slice scrolling, windowing, zoom/pan, measurements, multi-viewport layouts and 3D/MPR volume reconstruction on Cornerstone3D/WebGL
  • An LLM drives the viewer through a tool-use loop: selecting series, scrolling, re-windowing, measuring Hounsfield density, then drafting a structured report
  • AI-assisted reporting: shorthand-to-report expansion, multimodal slice second-look, voice dictation, patient-friendly summaries, all behind provider-agnostic ports
Next.js 16React 19Cornerstone3DVercel AI SDKZustandWebGL
dicom-viewer-production-b98b.up.railway.app↗
dicom-viewer/viewer/ncct-head · 3D MPR
DICOM viewer 3D workspace: MPR slices and volume-rendered skull of a head CT with signed report
IN PRODUCTION
03

AgentOS · Efficia

Enterprise Agent Platform · AvestaLabs

The factory that builds the agents. An enterprise suite to design, deploy, evaluate and monitor AI agents, architected from concept to production as founding engineer.

  • Agent orchestration with context engineering, RAG pipelines and vector-DB-backed agent memory
  • MCP client & server, a custom tools framework, and guardrails as first-class citizens
  • Eval-first architecture: simulate messy conversations, evaluate every edge case, auto-correct and loop
  • Companion products for LLM observability, RAG data-ingestion and evaluation
TypeScriptNode.jspgvectorMCPLangfuseEvals
avestalabs.ai · AgentOS co-workers
Avesta AgentOS: AI co-worker teams running sales, finance and support workflows in parallel
SHIPPED
04

view.com.au

Australian Real-Estate Portal

Complete rebranding and feature expansion of one of Australia's major property portals, led end-to-end on Next.js, Node.js and PostgreSQL.

  • Led feature delivery working directly with PMs and clients
  • Designed the implementation architecture and mentored the team on Next.js patterns
Next.jsNode.jsPostgreSQL
view.com.au↗
view.com.au
view.com.au homepage: property search Australia-wide

More on
GitHub

github.com/jeetsoni ↗

04Building in Public

One concept. One animation. One minute.

SynapByte is my animated engineering channel: one concept, one animation, one minute. Every single video is generated end-to-end by KalpanaAI, the platform I built. The content is the demo.

Instagram

1,400+

followers

@synap_byte ↗

AI & software engineering, animated. LLMs · system design · dev internals.

YouTube

73+

videos

SynapByte ↗

Nginx internals, UUID vs integer keys, CI/CD from scratch. Where every concept clicks.

Instagram

4,800+

followers

@jeetsoni.ai ↗

JS → production AI systems. RAG · agents · tools · UI. Real-world AI, not demos.

  • ✳Publication: “LLM-Based Chunking: Intelligent Text Splitting for Better RAG”, Avesta Labs Blog
  • ✳Contributing author: Aspire AI Academy Gen-AI Engineering Course
  • ✳1st place: AI-Driven Development Hackathon, Avesta HQ
05Arsenal

AI / LLM

AI Agents & Multi-Agent OrchestrationRAG PipelinesMCP (Model Context Protocol)Prompt & Context EngineeringFunction / Tool CallingEmbeddings & Vector Search (pgvector)Agent Evaluation & GuardrailsLLM Observability (Langfuse)Claude · Gemini · OpenAIVercel AI SDKMultimodal / VisionStreaming

Languages & Frameworks

TypeScriptJavaScriptPythonNext.jsReactNode.jsExpressNestJSAngular

Architecture

Clean / Hexagonal ArchitectureDomain-Driven DesignSOLIDDesign PatternsProperty-Based TestingCI/CD

Data · Cloud · DevOps

PostgreSQL + pgvectorMongoDBRedis · BullMQPrismaGraphQLAWS Lambda · API Gateway · DynamoDBCloudflare R2DockerTurborepoServerless
06Signal

Let's ship
something real.

Building an agent platform, wiring AI into a product, or hunting for an engineer who treats evals as seriously as demos? My inbox is open.

adesharajeet@gmail.com