Markov Chain Lab
Interactive learning platform for Markov chains, automata, and grammar conversion.
Open to opportunities
leptons1618@anishgiri.dev:~ whoami
Software Engineer
Building ML systems, full-stack apps & dev tools
I work at the intersection of machine learning, computer vision, and software engineering. I build practical systems that ship.
Selected Work
Deep dives
2026 · Full-Stack
AXCAD
A browser-based CAD application with a drawing engine, authenticated user management, and DXF/DWG interop. Built for engineers who need CAD workflows in the browser.
Read case study 2024 · SimulationMarkov Chain Lab
Interactive learning platform for Markov chains, automata, and grammar conversion.
Read case study 2023 · Computer VisionMenu OCR
A modular OCR pipeline that turns restaurant menu photos into schema-compliant JSON — sections, groups, items, and prices — with column-aware layout detection and global price-item matching.
Read case study 2024 · AI / MLEchoScript
Paste a YouTube link, get a transcript you can search and click to hear — Whisper already returns timestamps, so every line becomes a seek target back into the video.
Read case study 2026 · Full-StackPortfolio
Personal portfolio site for projects, case studies, and journal posts with a browser-based admin surface and AI authoring assistant. Content lives in Cloudflare D1, so publishing is a save rather than a commit.
Read case study 2026 · DevToolsAgent Workbench
A version-controlled AI engineering environment: agent skills pinned to exact commits, install profiles, and bootstrap scripts that leave upstream repositories untouched.
Read case study 2026 · AI / MLDaystorm
Daystorm fuses camera, CAN bus, radar, and cabin audio onto a causal 2 Hz grid so a language model answers grounded questions about a two-second driving window.
Read case study 2026 · DevToolsProofline
Proofline turns an audit or investigation into one self-contained HTML file — three visual modes, a print-safe layout, and an embedded JSON block that agents can parse and that never drifts from the prose.
Read case study 2025 · SystemsSIA Proto
A local-first system monitoring agent that tracks CPU and memory, stores events in SQLite, exposes a JSON-RPC CLI over Unix sockets, and optionally enriches insights via a local Ollama model — all within a 200 MB memory budget and a systemd service.
Read case study 2024 · Computer VisionVisionID
Face detection and recognition for live camera feeds — one build that runs on a Jetson, a CUDA desktop or a laptop CPU, with roles, audit and multi-camera sources.
Read case study 2023 · Full-StackStreamFusion
Synchronised watch parties with no account and nothing to install — an Expo client sharing playback over WebRTC data channels, with one small WebSocket server holding the room together.
Read case study 2026 · DevToolsKeySmith
A Go app for generating, managing and testing SSH keys, with a desktop GUI and a terminal UI over the same core — it shells out to OpenSSH, and the private key never leaves the machine.
Details 2026 · SystemsAI Perspective Builder
An Ignition module that docks an AI assistant into the Designer. The Designer holds a chat panel and nothing else — every model call crosses an RPC boundary to the gateway, and nothing reaches a project without a person approving it.
Read case study 2026 · Full-StackBhashaLens
A browser extension that shows Bengali word meanings, transliteration, and part of speech in a popup when you select text on any website. Backed by a Fastify API with a ~15k-entry dictionary.
DetailsMenu OCR
A modular OCR pipeline that turns restaurant menu photos into schema-compliant JSON — sections, groups, items, and prices — with column-aware layout detection and global price-item matching.
EchoScript
Paste a YouTube link, get a transcript you can search and click to hear — Whisper already returns timestamps, so every line becomes a seek target back into the video.
Skills & Stack
What I build with
ML / CV
HTMLHugging Face TransformerslxmlMLflowONNX RuntimeOpenCVOpenCV.jsPyTorchscikit-learnStreamlitTensorFlow.jsYAMLYOLOv8
Languages
GoJavaJavaScriptPostgreSQLPythonRustSQLiteSQLxTypeScript
Web
AstroCSSExpressFastAPINext.jsNode.jsReactReact NativeTailwindTailwind CSSViteWebAssemblyWebGLWebRTCWebSocket
Data & Infra
Cloudflare D1Cloudflare WorkersDocker
Also
AES-GCMaiohttpakinator.pyAtlassian APIBubble TeaBunCapacitorChromaDBChrome StorageChronoCIFAR-10ClapCUDADeepSortDeepStreamDioxusdiscord-componentsdiscord.pyDrizzle ORMExpoExpo RouterezdxfFaster-WhisperFastifyffmpegFlaskFyneGrad-CAMHerokuIgnition 8.1JDK 11JSONKerasLangChainLipglossMahalanobisManifest V3MarkdownMavenNiceGUINPMNumPyODINOllamaOpenAI APIOpenAI WhisperOpenSSHPaddleOCRPandaspdfplumberPlasmoPlotlyPowerShellPrismapsutilpypdfpyttsx3QLoRAReqwestSerdeShapelySheetJSShellspaCySpeechRecognitionSupabaseSwingsysinfosystemdTauriTensorRTTokioyt-dlpYuNetZustand
Contact
Let’s connect.
A role, a hard problem, a paper worth arguing about — send a transmission. Every message is read by a person, and answered.
$ whoami
leptons1618 — Software Engineer (ML/CV + Full-Stack)
$ cat contact.txt
EMAIL anishgiri163@gmail.com
LOCATION Bengaluru, Karnataka, India
LOCAL_TIME (Asia/Kolkata)
STATUS Open to opportunities · ML/CV, full-stack, systems
$ ping -c 3 anishgiri.dev
PING anishgiri.dev: 56 data bytes
64 bytes from edge: icmp_seq=0 ttl=57 time=— ms
64 bytes from edge: icmp_seq=1 ttl=57 time=— ms
64 bytes from edge: icmp_seq=2 ttl=57 time=— ms
3 packets transmitted, 3 received, 0% packet loss
$