Skip to content
View adimyth's full-sized avatar
🎯
Focusing
🎯
Focusing
19 followers · 4 following

Achievements

Achievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull Sharkx2Achievement: Arctic Code Vault Contributor

Block or report adimyth

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
adimyth/README.md

Hi, I'm Aditya 👋

Engineer working across infrastructure, backend, and AI/ML

🛠️ What I work with

  • Backend & Infra: Python, Go, FastAPI, PostgreSQL, AWS (EC2, RDS, VPC, MSK), Docker, Nginx/OpenResty
  • Data & Streaming: Apache Flink (PyFlink), Kafka, ClickHouse, Redis
  • AI/ML: Pipecat, LangGraph, Deep Agents, LangSmith, MCP, RAG

🌱 Currently exploring (Sep 2026)

  • Voice AI Stack: Real-time voice agents on Pipecat: speech in, an LLM with tools in the loop, speech back out.
  • LLM Inferencing: LLM Inference Experiments. Implementations and benchmarks for quantization, speculative decoding, and KV caching.
  • Memory in AI Agents: Memory Weave. A local memory layer for AI agents: evidenced records, hybrid retrieval, and a gate that can return empty so weak hits stay out of the prompt.

🎹 When I'm not coding

  • Learning to play piano
  • Reading books. Currently reading Surrounded By Idiots by Thomas Erikson
  • Functional fitness — strength training, mobility
  • Reading about systems design and getting opinionated about database indexes

📫 Let's connect

Open to chats about distributed systems, AI infra, or anything that involves making slow things fast.

Pinned Loading

  1. retold retold Public

    A local, provider-neutral memory layer for AI agents, with evidenced records, hybrid retrieval, and a usefulness judge that admits a record only if it would change the answer.

    Python

  2. realtime-streaming-systems realtime-streaming-systems Public

    Realtime Stream Processing using Apache Kafka & Apache Flink

    Python

  3. llm-inference-experiments llm-inference-experiments Public

    Runnable scripts behind the LLM Inference essays on adimyth.in

    Python

  4. self-hosted-video-recorder self-hosted-video-recorder Public

    A self-hosted video recording pipeline for Daily rooms with participant capture, layout composition, and MP4 encoding.

    Python

  5. async-job-processing async-job-processing Public

    A robust, scalable job queue system built with FastAPI, Redis Queue (RQ), and PostgreSQL. Features priority queues, scheduled jobs, automatic retries, and a CLI for job management, designed for rel…

    Python 5

  6. system-design-topics-implementations system-design-topics-implementations Public

    Implementing different system design techniques & algorithms

    Python 1 2