#8 AI Voice Engineer – Lead Our Dograha Stack (STT/TTS/LLM) on RTX 5090

Job Type & Collaboration Type: Long-term, ongoing monthly contract (multi-year vision). Schedule: Must be available for core collaboration hours daily within 6:00 AM – 4:00 PM EST (approximately 2–4 hours per day). Compensation & Partnership Model Monthly Retainer: $300 USD to start, with a defined path for substantial increases as system complexity and your responsibilities grow. Profit Sharing: You will receive a share of the 50% net monthly profit pool, which is distributed across the 5-person engineering team. Your specific role: You will be solely responsible for the Dograha instance, STT, TTS, and LLM stack. Your share of the profit pool will reflect the critical nature of this responsibility. This is a long-term, equity-like incentive directly tied to the value you create. Note: All code, models, configurations, and intellectual property developed during this engagement remain the sole property of the company. What We Already Have (You Are Not Starting from Zero) We have already built and are running a real-time AI voice pipeline. We have shifted our architecture to use Dograha (an open-source Vapi alternative) as our foundation. Our system runs on a single machine with an NVIDIA RTX 5090 GPU. Currently Running: Dograha Core: The base framework is installed and operational. STT & TTS: Integrated speech-to-text and text-to-speech models. Pinecone: Vector database connected to our Fusion PBX for memory/context. Custom Portal: A basic Vapi-style dashboard for managing voice agents. Your Mission: Take our existing Dograha instance and complete the migration to fully replicate Vapi's feature set (see below). You will optimize, scale, and maintain the platform to ensure it is a robust, self-hosted alternative to Vapi. Required Features (We Need to Build / Complete) We have upgraded to Dograha and are integrating additional services (STT, TTS, LLM). The goal is to replicate Vapi's functionality completely. Key modules we still need to configure and enhance include: Module Details Assistants Create, edit, delete voice assistants (Dograha native). Squads Group multiple assistants/numbers for load balancing/IVR. Tools Function calling and custom integrations via Dograha. Phone Numbers Provision and manage inbound/outbound numbers (SIP trunking). Logs Call recordings (listen back), transcripts of assistant + user dialogue. Voice Library Manage TTS presets and custom voices. Metrics Total call minutes, number of calls, costs, etc. Integrations Configurable list of third-party integrations (CRM, etc.). API Keys Generate and manage API keys for programmatic access. If you are familiar with Vapi's UI/API and Dograha's architecture, you already know the target. Technical Scope Current Stack (Already Running) Real-time AI voice pipeline (STT → LLM → TTS) on RTX 5090. Dograha as the core automation framework. Pinecone for memory/context. Fusion PBX (SIP telephony). Custom portal (Vapi-style dashboard). Your Responsibilities (Sole Accountability for the AI Stack) Migration & Enhancement: Upgrade the current Dograha installation to handle the missing modules (Assistants, Squads, Tools, Logs, Voice Library, Metrics, Integrations, API Keys). Low-Latency Optimization: Use TensorRT, vLLM, or similar to optimize models for ultra-low latency. System Integration: Ensure seamless interaction between Dograha, Pinecone, Fusion PBX, and the dashboard. Self-Hosted Stability: Harden the system for production use (logging, alerting, backup). Long-Term Scalability: Scale the system to multi-GPU or multi-node as we grow, and maintain uptime. Team Collaboration: You will work alongside 4 other engineers who handle other parts of the platform (frontend, telephony infrastructure, devops, etc.). However, you have sole decision-making authority and accountability over the Dograha instance and all AI models (STT, TTS, LLM). Required Technical Expertise (Must Demonstrate) AI/ML Deployment: Proficient with PyTorch, TensorRT, vLLM, or llama.cpp. Experience fine-tuning ASR/LLM models is a plus. Real-Time Voice Pipelines: Hands-on experience with STT (e.g., Whisper, Faster-Whisper) and TTS (e.g., Coqui, XTTS, or cloud alternatives). Dograha & Vapi Experience: You must understand the architecture of Dograha and how it mimics Vapi's functionality. You know how to extend it. Telephony Engineering: SIP protocols, integration with PBX systems (we use Fusion PBX). Familiarity with PJSIP or Asterisk is a big plus. Backend & Dashboard: Ability to build/extend a web portal (we already have a base – you'll work on the API and frontend as needed). Infrastructure: Linux, Docker, basic GPU optimization. A security-minded approach is required. Why Join This Project? You are not starting from scratch – the core pipeline and Dograha instance are already installed and running. Direct profit sharing – You receive a share of the 50% net monthly profit pool, distributed across the 5-person team. As the engineer solely accountable for the Dograha/STT/TTS/LLM stack, your share reflects your central role. High ownership (of responsibility), high impact – You are not a cog in the machine. You own the outcome and performance of the platform's brain. Long-term, founding-level role – Shape the architecture and grow with the company. Work on cutting-edge AI + telephony – Real-time voice agents are the future of customer interaction. How to Apply Send a brief message explaining: Your experience with real-time STT/TTS pipelines and low-latency LLM serving. Your familiarity with Dograha and/or Vapi (or similar voice agent platforms). Any work you've done with SIP / PBX integration. Your availability during the core hours (6 AM – 4 PM EST). Please note: You will be joining a team of 5 engineers total. While the 50% profit share is split across the team, you will have sole accountability and responsibility over the Dograha instance, the AI models (STT/TTS/LLM), and voice management. All intellectual property developed remains company property. This is a high-impact, high-accountability role within a collaborative environment.