Building a Multi-Agent Research Pipeline with LangGraph
How I built Orchestra — a production-grade research orchestration system with 5 specialized agents working in concert.
Read more →AI Engineer — Bangalore, India
Hi, I'm
Sneh Sinha
(scroll)
■ About
An AI engineer from Bangalore, building at the intersection of intelligence, infrastructure, and the physical world.
// profile.ts
interface Engineer {
name: "Sneh Sinha";
location: "Bangalore, India";
role: "AI Engineer";
vibe: "building";
}
I'm an AI engineer from Bangalore who builds systems at the intersection of artificial intelligence, robotics, and cloud infrastructure. I believe the most interesting problems live where software meets the physical world.
Currently exploring multimodal AI agents, computer vision on edge hardware, and autonomous cloud operations. I work with Python, Rust, C, and whatever else gets the job done.
When I'm not shipping code, you'll find me tinkering with ESP32-CAM modules, optimizing LLM inference pipelines, or reading about distributed systems.
■ Experience
Building in
Public
RoleAI Engineer
FocusMultimodal AI, Agents, Infra
StatusShipping
(01)
2026 — Present
Team Stratos
AI EngineerBuilding multimodal AI agents and autonomous systems at the intersection of computer vision, LLMs, and cloud infrastructure.
(02)
2025 — Present
DeepOps
Creator & Lead DeveloperAI-powered autonomous cloud operations platform. Natural language infrastructure management, anomaly detection, auto-remediation.
(03)
2025
Orchestra
Creator & Lead DeveloperProduction-grade multi-agent research orchestration with LangGraph, FastAPI, PostgreSQL, and Prometheus.
(04)
2025
PromptOS
Creator & Lead DevelopermacOS desktop app — prompt compiler with multi-pass optimization, WASM plugins, local LLM inference via Metal GPU.
(05)
2025
ESP32-CAM Vision Suite
Embedded Systems EngineerThree ESP32-CAM projects: ML dataset capture, real-time color tracking robot, 60 FPS MJPG streaming server.
(06)
2024 — Present
Open Source
ContributorActive open source contributions. Building tools for the AI and developer community.
(01)
I believe the most interesting problems live where software meets the physical world.
Every project is an experiment in what happens when you ship fast and iterate relentlessly.
■ Skills
Tech &
Tools
Languages
AI & ML
Backend & Infra
Embedded & Edge
Tools & Platforms
Languages5+
Frameworks12+
ExploringMultimodal Agents, Cloud, Edge
(02)
Full-stack AI engineer comfortable from embedded firmware to cloud orchestration.
The best tools are the ones that get out of your way when you're in flow.
■ Projects
What I've
Built
(01)
DeepOps
AI-powered autonomous cloud operations platform that behaves like an experienced SRE team. Deploys, monitors, detects anomalies, and repairs services automatically.
GitHub →
(02)
Orchestra
Production-grade AI research orchestration with 5 specialized LangGraph agents — search, extract, verify, synthesize, critique — producing verified reports with confidence scoring.
GitHub →
(03)
PromptOS
macOS desktop app that treats prompts as source code — compiles through a multi-pass optimization pipeline with WASM plugins, local LLM inference, and cloud provider support.
GitHub →
(04)
ESP32-CAM Vision Suite
Three ESP32-CAM projects: web-based image capture for ML datasets, real-time color tracking robot, and full-featured MJPG video streaming server at 60 FPS.
GitHub →(03)
Every project is open source. Code speaks louder than words.
Building in public means shipping fast, breaking things, and learning out loud.
■ Open Source
GitHub
Pulse
—
Repos
—
Contributions
—
Languages
—
Followers
—
Stars
Contribution Graph
■ Competitive
LeetCode
Profile
—
Total Solved
—
Global Rank
(01)
Competitive programming keeps my fundamentals strong. I solve DSA problems to stay sharp.
■ Writing
Thoughts &
Ideas
DeepOps: An Autonomous SRE Platform
Designing a cloud operations platform that deploys, monitors, and heals itself — inspired by how humans reason about incidents.
Read more →Computer Vision on ESP32-CAM: A Practical Guide
Real-time HSV tracking, MJPG streaming, and ML dataset collection on constrained hardware. What I learned building the Vision Suite.
Read more →
Bangalore, India
Open to work
© 2026 Sneh Sinha
v2