-:-:- · SURAT, IN
backend & systems engineersurat, india
Backend & Systems Engineer
ml, dl & llm harness implementation - inference, agents, mcp, on-device
Founding Engineer @ Saras - building the systems & AI behind advisor intelligence over live-market data.
Backend engineer who finds zen in the terminal. New tech drops and I go feral to reverse-engineer it. A 1000x extrovert with people I know, a 10000x introvert with everyone else. Big-time overthinker, terminal-over-IDE kinda guy.
BACKENDSYSTEMSAIINDIE OSS
now playing
nothing rn
offline · zzz
-:--
current stack
python
pytorch
vllm
go
postgres
cloudflare
typescript
recent writing
Two Gates and a Process Boundary: Swapping vLLM's Suffix Drafter Without a ForkSwapping vLLM's suffix drafter without a fork: two gates in two processes, one import-binding mistake, one process-boundary mistake, and the plugin fix.Jul 20269 minslate: Turning a Phone into a Stream Deck for macOS - One Command, a Pluggable Backend, and the Trade-offs Behind ItHow I built slate, a free open-source phone-as-Stream-Deck for Mac over your LAN with no cloud: one Command, a pluggable Transport, one shared Zod schema.Jul 202620 minNo Public Ports: Zero-Trust Team SSH to a Private Azure Cluster with a Reverse Bastion and Cloudflare WARPTeam SSH to a private Azure dev cluster with zero open ports: one outbound cloudflared bastion, Cloudflare WARP, Google SSO, and the split-tunnel routing trap.Jul 202617 minBear the Tokens: FP16 and Suffix Decoding to 9,000+ Tokens a Second on a Tesla T4Pushing Qwen2.5-0.5B to 9,052 tok/s on a free Colab T4 in the H2Loop contest: AWQ INT4 dead ends, FP16, and model-free suffix speculative decoding.Jun 202621 minLogpipe: Building a Distributed Logging Stack from Scratch with Vector and ClickHouseHow I built Logpipe, a small but real Vector + ClickHouse logging pipeline in Go: why aggregator batching matters, 'Too many parts', and disk buffers.Jun 202625 minTapTalk: Building a Free, Local, Open-Source Alternative to SuperWhisper and Whisper FlowHow I built TapTalk, a free local speech-to-text app for macOS in Rust and SwiftUI: Whisper on the Neural Engine via Core ML, chip-tuned, push-to-talk.May 202621 minThe Three Levers: Backend-Driven UI, OTA Updates, and the End of Waiting for App ReviewHow Swiggy, Airbnb, PhonePe and Nubank ship UI without app store review, and how I built a BDUI + OTA system in React Native with Cloudflare Workers and EAS.Apr 202618 minHow a Roblox Cheat Script Took Down Vercel: Anatomy of a Supply Chain BreachDissecting the April 2026 Vercel breach: infostealer malware to OAuth hijack to customer data exposure. Full kill chain, trust lessons, survival guide.Apr 20269 minBuilding a Real-Time F&O Fair Value Engine for Indian MarketsHow we built a production fair-value calculator on top of Dhan - Black-Scholes, cost of carry, live depth, and mispricing signals - for Saras and NSE F&O.Apr 20267 minBuilding a World-Monitor News Engine for Traders: From ~115 Public Sources to a Daily BriefHow we built Saras's agentic news engine: scrape public macro and trade intelligence, dedupe at scale, enrich with structured AI, ship a trader-facing brief.Apr 20267 min