Skip to content

> software_engineer :: full_stack

DhruvRishishwar

Full-stack engineer building LLM agents, RAG pipelines, and query engines that scale. At Enso I cut p95 latency from 26s to under 1s and shipped the platform's busiest endpoint — 53K requests a week.

26s → <1s

Query p95

53K / week

Top endpoint

31 objects

Agent coverage

Dhruv Rishishwar, full-stack software engineer specializing in LLM agents and query engines

// 02 Stack

Tools I reach for when the problem is real.

PythonJavaScript/TypeScriptSQLGoRustReact.jsNext.jsNode.jsFlaskRESTful APIsTool-Calling LLM AgentsRAGVector EmbeddingsSemantic SearchSentence TransformersOCR (AWS Textract)CUDAPostgreSQLMySQLClickHouseRedisQdrant (Vector DB)Query OptimizationMicroservicesApache KafkaCeleryDistributed ArchitectureAWSDockerCI/CDJenkinsPrometheusGrafanaGitPythonJavaScript/TypeScriptSQLGoRustReact.jsNext.jsNode.jsFlaskRESTful APIsTool-Calling LLM AgentsRAGVector EmbeddingsSemantic SearchSentence TransformersOCR (AWS Textract)CUDAPostgreSQLMySQLClickHouseRedisQdrant (Vector DB)Query OptimizationMicroservicesApache KafkaCeleryDistributed ArchitectureAWSDockerCI/CDJenkinsPrometheusGrafanaGit

Programming Languages

PythonJavaScript/TypeScriptSQLGoRust

Frontend & Full-Stack

React.jsNext.jsNode.jsFlaskRESTful APIs

AI & LLM Systems

Tool-Calling LLM AgentsRAGVector EmbeddingsSemantic SearchSentence TransformersOCR (AWS Textract)CUDA

Databases

PostgreSQLMySQLClickHouseRedisQdrant (Vector DB)Query Optimization

Distributed Systems

MicroservicesApache KafkaCeleryDistributed Architecture

DevOps & Cloud

AWSDockerCI/CDJenkinsPrometheusGrafanaGit

// 03 Work

Shipped under load, then made it faster.

  1. [2025] WRITE Enso

    Enso logo
    EnsoCurrent

    Software Engineer (Full Stack)

    — · Bengaluru, India

    • Python
    • TypeScript
    • React.js
    • AWS
    • Qdrant
    • ClickHouse
    • LLM Agents
    • RAG
    • Designed and built Enso's reporting/query engine from scratch, scaling into the platform's top endpoint (53K requests/week, 43x the next-busiest).
    • Root-caused and fixed a critical latency bottleneck in the query engine, cutting p95 latency from 26s to under 1s and dashboard load from 34.7s to under 5s.
    • Developed Enso's first AI agent from scratch: a tool-calling LLM agent generalized across 31 business object types via a 6-verb meta-toolkit, gated by staged write confirmations.
    • Engineered a contract-intelligence pipeline (AWS Textract OCR + retrieval-augmented LLM parsing via Qdrant) with a self-improving few-shot loop.
    • Led the proposal and solo development of a ClickHouse-based solution for high-volume event data, building the query-API layer across two distinct services.
  2. [2024] DONE Cisco Meraki

    Cisco Meraki logo

    Technical Intern 1

    — · Bengaluru, India

    • Python
    • Ruby
    • React
    • Flask
    • SQLite
    • Selenium
    • Jenkins
    • Docker
    • Architected a custom integration server bridging Ruby and Python testing frameworks, enabling cross-team code reuse and reducing QA cycle time by 25% through streamlined test execution workflows.
    • Delivered OAuth-enabled chatbot features with group chat and advanced context management capabilities, contributing to the product's successful market launch with multi-user support and enterprise-grade authentication.
    • Built a scalable UI testing framework in Ruby using Selenoid, Capybara, and SitePrism, automating 5+ critical user flows and reducing manual testing overhead by 40% while improving release reliability.

// 04 Selected work

Search engines, games, and products shipped end to end.

// this_site

Built with Next.js 16, React 19, and TypeScript — compiled with Turbopack for lightning-fast page loads.

The interface now runs on Tailwind, GSAP, and Motion, with a design system that stays elegantly responsive across every page.

Next.js 16React 19TypeScriptTurbopackTailwind 4GSAPMotionPowerGlitchJSONMarkdownrapid updatesno UI rewrite
SneakDex project screenshot

featured / sneakdex

SneakDex

Built a high-performance, distributed semantic search engine using Python, Go, Rust, and modern cloud-native tools. Delivers lightning-fast, relevant results at scale.

PythonGoRustNext.jsTypeScriptDockerRedisKafkaVector DB

live engine · ⌘K from anywhere

On The Way project screenshot

project / ontheway

On The Way

Engineered a robust student counseling platform with real-time features and a modern React/Node/MySQL stack.

ReactNodeMySQL
Sentinel project screenshot

project / sentinel

Sentinel

Created an offline voice assistant in Python, enabling smart automation without internet dependency.

Python

// 05 Writing

Notes on systems, memory, and time.

Essay

The Theory of Time

An exploration of time's nature through physics and philosophy—from Einstein's relativity to the arrow of time and temporal paradoxes.

Read more