Sarim

Search Blogs...

hey, I am Sarim 👋🏼

As an innovative Senior AI Software Engineer at Mira, I specialize in developing AI-driven solutions and scalable systems. From architecting RAG agents to building developer tools, I focus on creating high-performance applications that solve complex problems while maintaining technical excellence.

"All human wisdom is contained in these two words - Wait and Hope." ― Alexandre Dumas, The Count of Monte Cristo

my work

Mira

Senior AI Software Engineer

  • Led and architected 'Klok' a crypto-focused RAG agent with 10,000 users and 150 daily active users, developing pricing-based, temporal-based, and general query flows using BAML for flow management, Pathway for data ingestion and data retrieval, and implemented Redis for caching and FastAPI for backend development to ensure high performance and scalability.
  • Developed and maintained a Python SDK for the Mira API, facilitating seamless integration and execution of AI-driven flows and components. Designed a flow management system with YAML configurations for flexible and scalable flow creation and execution.
  • Developed and maintained a command-line interface (CLI) tool using Go and the Cobra library, enhancing user interaction and operational efficiency by implementing features for API key management, flow deployment, and execution with JSON and YAML configurations.
  • Mentored junior developers in Next.js, FastAPI, Redis, and Docker, enhancing their technical skills and contributing to team growth.
  • Tech Stack: FastAPI, Langchain, Pathway, TypeScript, React, Next.js, Python, Docker, AWS, Azure, GCP, SDXL, ComfyUI

WT Studios

Founding Engineer

  • Architected and deployed AI-powered chatbots for Telegram and Discord platforms, enhancing user engagement with domain-specific knowledge. Leveraged Langchain for efficient embedding creation and Qdrant DB for high-performance vector storage and retrieval.
  • Developed an AI-driven question series generator leveraging entity extraction techniques, improving bulk question generation quality.
  • Led the architecture and development of an AI-powered video script generator application:
  • - Developed a full-stack application using Next.js, where users can input topics to generate 60-second short video content with AI.
  • - Implemented backend processing with Inngest and Cloudinary to fetch images, use Tortoise TTS library for voice generation, and combine elements with RemotionJS and background sound to produce high-quality video content in bulk.
  • Tech Stack: Next.js, Inngest, Cloudinary, Tortoise TTS, RemotionJS, Langchain, Qdrant DB

ListenUp

Software Developer Intern

  • Improved database schema design in mongodb so as to increase efficiency of querying and reduce data redundancy.
  • Accomplished a rating system using React Native's PanResponder API where a user can swipe or touch to rate a song, it keeps saving until a user has finally decided on a rating and also giving ability to cancel at any time.
  • Designed an artist tagging feature where an artists can credit another artist and it will link profile of respective artist while also checking whether tagged artist is an artist or not.
  • Performed a backend functionality where a check is kept whenever a subscription has ended, thereby alerting user to either subscribe again or to cancel.

StaderLabs

Full Stack Intern

  • Analyzed and developed web application using NextJS with team of 5 UI developers; interacted with 2 Senior Project Managers to gather requirements for front-end development tasks.
  • Created a ToDo application using TerraJS to explain various concept of blockchain, such as transaction but making it simple of how a blockchain works.
  • Designed and developed a website so as to introduce the Stader team and also launch dates of various products of StaderLabs.
© 2024 Sarim Ahmed