About Me
I'm Sahil Malik, a Sr. Software Development Engineer at Amazon based in Seattle. Over the past decade at Amazon, I've worked across the entire spectrum of software engineering — from payment systems to building ML inference platforms that serve all of Alexa's voice traffic.
I'm a co-inventor on US Patent 12,494,194 B1 for an ML inference architecture that enables incremental, asynchronous processing using neural network subgraphs — improving responsiveness in real-time speech and NLU systems.
Outside of Amazon, I build AI research tools on my personal NVIDIA DGX Spark setup — a multi-blueprint lab with 15+ ML models spanning LLM orchestration, voice cloning, video generation, and autonomous agent systems. I also created vaani, a Hindi-based programming language designed to make computing accessible across linguistic barriers.
I'm originally from Haryana, India. I studied Computer Engineering at NIT Kurukshetra (CGPA 8.99/10), interned at Amazon, and have been here ever since — growing from SDE-1 to Sr. SDE across 7 roles and teams.
Career Timeline
Sr. Software Development Engineer
Agent AI systems, LLM latency optimization, and developer tooling.
- •Significant latency reduction in LLM-based chat through parallelization and caching
- •Driving migration to modern agent frameworks
- •Built developer tooling for AI-assisted debugging with MCP integration
Sr. Software Development Engineer — Alexa+
LLM service architecture, agent orchestration, and cross-org technical leadership.
- •Demonstrated sub-2-second Alexa response latency in cross-team demos
- •Led technical support team for Alexa+ public launch event
- •Authored monolith-to-microservices architecture proposal reviewed by senior leadership
- •Drove cross-organization alignment across 6+ teams
Sr. Software Development Engineer
Self-learning arbitration systems and containerized microservices.
- •Built self-learning arbitration systems
- •Subject matter expert for containerized microservices and cloud infrastructure
Software Development Engineer II — Alexa AI
Founding member of an ML inference platform team. Grew the platform from serving a small fraction to 100% of Alexa voice traffic.
- •Delivered a production Tier-1 ML inference service hosting 30+ models
- •Built an NLU disambiguation feature serving millions of customers monthly
- •Expanded ML-based routing to 11 locales across 8 languages
- •Co-invented US Patent 12,494,194 B1 for ML inference architecture
Software Development Engineer II — Payments
Financial products platform development.
- •End-to-end owner of a customer differentiation module
- •Prototyped NoSQL migration for millions of customer records
Software Development Engineer I — Gift Cards
Gift card services, security features, and API development.
- •Built refund processing system impacting tens of thousands of customers
- •Designed and implemented security features for the gift card claim flow
- •Developed 5 APIs with >95% test coverage
Software Development Engineer Intern
Summer internship, converted to full-time offer.
B.Tech Computer Engineering
CGPA: 8.99/10.0