Suyash Singh

AI Researcher & Software Engineer.

Bengaluru, IND

About

•

I'm a Computer Science Engineering student and published AI researcher based in Bengaluru, India, building production-grade AI systems, LLM pipelines, and highly scalable backend infrastructure.

•

I focus on memory-augmented agentic workflows, machine unlearning frameworks (GDPR compliance), and high-performance Rust/Go backends.

Contact

GitHub

Mail

Call

Experience

Stealth Startup

AI Intern

dec 2025 – may 2026

Built backend systems for an LLM-powered conversational AI platform using Mistral with memory-augmented agentic workflows and multi-turn dialogue.

Integrated NLP-based entity and intent extraction to capture structured data from unstructured user inputs.

Designed REST APIs and AWS-based inference services handling conversation state, routing, and session management at scale.

IEEE Computer Society

R&D Intern — Bangalore Chapter

apr 2025 – sep 2025

Authored technical workshop documentation on AI and systems topics, materials used across sessions attended by 100+ students across multiple cohorts.

Distilled recent research papers into structured, beginner-accessible write-ups used as official workshop references and onboarding material.

Projects

View all

Semantic LLM Gateway

API proxy acting as an intelligent cache & cost-aware router for LLMs with semantically stored hits (<50ms caching).

The Watcher (AIOps)

Auto-remediation system running anomaly detection models at the edge for Kubernetes microservices (handles 5k+ RPS).

SENNs (Unlearning)

ICDDS 2025

GDPR-compliant machine unlearning frameworks designed to erase neural network data without full retraining.

Writing

Self-Erasing Neural Networks (SENNs): GDPR-Compliant Unlearning Published in ICDDS 2025

# ask why Suyash matters