Open to opportunities

Siddhant Rai

@siddhantrai

Message

Software engineer specializing in backend systems, LLM agents, and scalable infrastructure.

India

Message

What I'm looking for

I seek roles building production-scale backend and LLM systems where I can drive architecture, improve reliability and latency, and ship autonomous, secure infrastructure in collaborative engineering teams.

I am a software engineer focused on backend systems, large-language-model agents, and building production-ready, high-concurrency distributed systems. I design and ship scalable architectures — from routing layers for specialized LLMs and vector-based retrieval to multi-tenant AI platforms — that improve latency, concurrency, and reliability in real-world deployments.

My work includes optimizing RAG pipelines to support 50% more concurrent users while cutting P99 latency by 38%, engineering secure autonomous agent integrations with OAuth 2.1, and implementing automated testing to reduce regressions by 40%. I pair strong algorithmic foundations (LeetCode 2040+) with practical experience across Python, Go, cloud infrastructure, and system design to deliver resilient, observable services.

Experience

Work history, roles, and key accomplishments

Current

Software Engineer

Current

Arc53

Apr 2024 - Present (1 year 10 months)

Architected a routing layer for LLM agents enabling query delegation to specialized models, handling 50% more concurrent users and reducing P99 latency from 8.2s to 5.1s; improved retrieval with Qdrant for 10,000+ monthly queries and introduced automated response testing, cutting regression bugs by 40%.

Python LLM Flask Semantic Search Caching Distributed Systems

Full Stack Engineer Intern

PropReturns

Apr 2023 - Jun 2023 (2 months)

Built a reusable UI library used across 3 internal apps, accelerating frontend delivery by 40% and optimized Core Web Vitals to reduce LCP by 400ms via code-splitting and CloudFront caching, improving SEO.

Next.js React AWS Bit.Dev CI CD Visual Regression Testing JavaScript

Full Stack Intern

Pinch Finance

Jun 2022 - Nov 2022 (5 months)

Developed and deployed 20+ scalable RESTful APIs handling 10,000+ requests/day with 99.5% reliability and optimized SQL queries with indexing to reduce critical-flow latency by ~300ms.