Full Stack Founding Engineer (GenAI)

A real-time AI-powered meeting assistant designed to revolutionize online communication . A &aposJarvis for online meetings&apos, empowering users to communicate smarter and drive better business outcomes. (https://jarwizai.com)

The real-time AI-Meeting co-pilot/companion ( built on Agentic-Rag framework & reinforced with NLP models) participates in online meetings, listens, analyzes, and provides real-time contextual prompts, completes actions, does web search, updates CRM, etc on your behalf.

Remote / Full-Time / Stipend - INR 30K-50K / 0-2 years work ex / BE/BTech/Mtech (final year/graduated)

Responsibilities:

• Engage in GenAI/NLP projects that incorporate the latest developments in LLMs, RAGs, and AI Agents.
• Research and implement advancements in Prompt engineering, RAGs, Multi-Agentic AI, and model fine-tuning to create innovative AI solutions.
• Design and build GenAI applications using LLM and AI tools.
• Code, test, and iterate on various product hypotheses utilizing advancements in multimodal AI.
• Conduct thorough testing and debugging to ensure high-quality, performant AI software.

Requirements:

• Prior hands-on FullStack development experience with the stack Next.js, FastAPI, AWS, PostGres, Prisma, MongoDB.
• Prior experience in GenAI/LLM projects.
• Hands-on experience with RAG, Agents, Evals, and Datasets.
• Familiarity with AI Agent frameworks, such as Langgraph, Crew AI, LangChain, and LamaIndex.
• Knowledge of no-code/low-code platforms like Replit, Vercel, and Cursor AI.

Tech skills you should be familiar with:

• Frontend: Next.js, TypeScript, WebSockets
• Backend: Python (FastAPI / Flask), PostgreSQL
• Infra: Docker, Kubernetes, AWS/GCP, Vercel AI/GenAI:
• STT / TTS (Whisper, Deepgram)
• RAG (LangChain, LlamaIndex, Weaviate / Pinecone)
• Agentic AI (LangGraph, CrewAI)
• Real-time audio/video processing (WebRTC, )
• Other: Firebase, Supabase, REST APIs, No-Code/Low-Code (Replit, Streamlit)