Suryansh Singh

Building production-grade AI systems and agents that are scalable, performant, and actually used.

Experience

A

Arivihan Tech.

Sept 2025 - Present
AI Engineer
I

Invsto Inc.

Nov 2024 - Sept 2025
Full Stack Engineer

Blogs

View All

Serving LLMs: What Actually Determines Your Throughput and Latency

The infrastructure half of GenAI: prefill vs. decode, why the KV cache is your real constraint, continuous batching, quantization trade-offs, and how to plan capacity without guessing.

Aug 25, 2026

LLMOps: Evaluation, Observability, and Shipping Without Fear

How to take an LLM feature from a notebook demo to something a team can change safely — eval sets built from real traffic, honest grading methods, CI regression gates, and production tracing.

Jun 15, 2026

Projects

View All
Instant Guru

Instant Guru

Multimodal AI tutoring agent for Indian students (Class 10–12), live in production on the Arivihan app. Accepts image, text, and audio inputs and produces text or image responses. Uses chain-of-thought reasoning and an advanced subagent architecture with specialists for doubt solving, content search, and guidance — with multilingual understanding (Hindi, English, Hinglish) and real-time streaming.

LMS

Built departmental ERP with QR-based attendance, internal forms, assignment management, and open-source simulator integrations. Integrated testing module with auto-evaluation, results summary, and email delivery. Automated Excel/PDF report generation. Deployed on college intranet using Nginx + PM2; used by 500+ daily.