STSridharan T

Software engineer / India

Open to product engineering roles

I build thesystems behindintelligent products.

I'm Sridharan, a Software Engineer at Aspire Systems. I help build a campaign platform serving 50K+ users and independently ship open-source AI infrastructure and developer tools.

Selected workHow I work
GitHub LinkedIn

Interactive proof / inspect a system

See how the work moves.

Social Media Agent

01 / 03

Agent routing

One campaign idea becomes four platform-specific drafts through a stateful LangGraph workflow.

Input

One idea

System

LangGraph router

State

Memory + retries

Output

4 drafts

Open source · retries + memory checkpointing

LangGraphOpenAIAnthropic Source

Showing Agent routing: Open source · retries + memory checkpointing.

Choose a system to inspect.

Evidence, not theatre

50K+

users on a platform I help build

View context

40%

lower API latency after query and pipeline work

View context

30%

lower media-storage cost through S3 workflows

View context

Selected work

Proof over promises.

Three builds, three different constraints: agent orchestration, cognitive-load-aware planning, and reviewable AI edits inside the editor.

3 selected case studies / 9 builds in the archive

01 / AI & Automation2025 · Open source

Social Media Agent

One graph. Four platform-specific draft flows.

A LangGraph workflow that turns one campaign idea into platform-specific drafts for LinkedIn, Twitter/X, Facebook, and Instagram—adapting tone, length, and hashtag strategy for each channel.

  • Orchestrated parallel platform branches via LangGraph StateGraph with memory checkpointing
  • AI rewrites content per platform: 280-char Twitter punchy vs long-form LinkedIn professional
PythonLangGraphLangChainOpenAIAnthropicDocker
Source code
02 / Product Systems2025 · Prototype

FocusFlow — AI Task Manager

Context-aware scheduling designed around cognitive load.

A task-planning PWA exploring cognitive-load-aware scheduling. Google Genkit prioritizes tasks using current time and workload context, with real-time push notifications on iOS.

Next.js 15FirebaseGoogle GenkitPusher
Source code
03 / Developer Tools2025 · Open source

AI Code Assistant — VS Code Extension

Keyboard-first AI edits with reviewable inline diffs.

A VS Code extension with Ghost Chat—a cursor-positioned AI panel that previews inline diffs before any change is applied.

TypeScriptVS Code APIWebViewMonaco Editor
Source code

Want to inspect the implementation? The full archive links each public build to its source, stack, and key engineering decisions.

See the full archive

One build / end to end

An AI model you can carry in one file.

I turned an embedding model into a portable service that runs without Python or a network—and ships across three operating systems.

Inspect the source
embedding-server

22MB

Model + tokenizer + runtime + API

LINUXWINDOWSMACOS
  1. 01

    Request

    POST /v1/embeddings

    Plain text enters a small, predictable REST contract.

  2. 02

    Inference

    ONNX + MiniLM

    The bundled model returns a 384-dimensional embedding.

  3. 03

    Package

    Nuitka standalone

    Model, tokenizer, runtime, and API become one 22MB binary.

  4. 04

    Deliver

    Three operating systems

    GitHub Actions builds Linux, Windows, and macOS; Docker stays available.

Offline

Runs without a network

Zero setup

No Python required

22MB

Standalone executable

384

Embedding dimensions

Experience

From trainee to production ownership.

A steady progression at Aspire Systems—from learning the stack to owning systems that carry real users, costs, and reliability expectations.

Career path

Aspire Systems

  1. Apr 2024 — now

    Software Engineer

    Production platforms, AI integrations, and delivery ownership.

  2. Jan 2024 – Mar 2024

    Trainee Engineer

    Contributed backend service development in Node.js and Laravel for production platform features

  3. Jan 2023 – Mar 2023

    IMPACT Trainee

    Completed structured full-stack training covering JavaScript, Node.js, MongoDB, and REST APIs

Current role

Software Engineer

Aspire Systems

Apr 2024 – Present

Core product flows

Campaign management, analytics, delivery tracking, and rich-text email creation.

System performance

MongoDB query tuning, response pipelines, and media-storage paths shaped around scale.

Applied AI

Content moderation, generation workflows, and citation-aware realtime chat behavior.

Delivery ownership

Reusable npm packages, WebSocket interfaces, and GitHub Actions deployments to AWS.

The common thread is end-to-end responsibility: follow the behavior from the interface through the API and data layer, then carry it into production.

Capabilities, not percentages

From constraint to working software.

A stack list says what I've touched. This is how I use it: frame the right problem, connect the system, design the recovery path, and carry the build into use.

Phase 01 / Frame

Name the real constraint.

“What must become measurably better?”

I start with the user path, the system boundary, and the signal that will tell us the work actually helped.

Working output

  • Success measure
  • Failure boundary
  • Smallest useful slice
Tools in this phaseSystem mappingAPI contractsProduct thinking

Showing Frame: Name the real constraint.

Working stack

01

Production core

TypeScript · Node.js · MongoDB · Laravel

02

Applied AI

Python · LangGraph · OpenAI · ONNX

03

Product interface

React · Next.js · Vue · Tailwind CSS

04

Delivery

Docker · AWS · GitHub Actions · Vercel

About / How I work

Curious enough to explore. Practical enough to ship.

I'm a Salem-based software engineer at Aspire Systems. At work, I help ship an email-marketing platform used by 50K+ people; outside work, I build open-source AI infrastructure and developer tools.

I'm drawn to problems that cross boundaries—model behavior, API design, performance, packaging, and UX. My best work begins with a measurable constraint and ends with something another person can run, inspect, and maintain.