AI/ML Engineer

Job Description

Role Overview: We are seeking an experienced Voice Agent Developer with a strong background in Large Language Models (LLMs), Natural Language Processing (NLP), Text-to-Speech (TTS), and Speech Recognition. The successful candidate will be responsible for designing, developing, and deploying a high-performance voice agent system. You will work closely with our frontend team to ensure seamless integration and exceptional user experience. ⸻ Key Responsibilities: • Design and develop an intelligent voice agent using LLMs (such as OpenAI, GPT, or similar models). • Integrate Text-to-Speech (TTS) using Eleven Labs or other advanced TTS systems. • Implement Speech Recognition using Whisper API or other leading ASR (Automatic Speech Recognition) technologies. • Develop real-time voice interaction logic with user-friendly voice input and output. • Optimize voice agent performance for low-latency, high-accuracy interactions. • Implement context management to maintain coherent user conversations. • Work closely with the frontend development team to integrate the voice agent with a user-friendly interface. • Ensure robust error handling and fallback mechanisms for voice interactions. • Conduct extensive testing for voice quality, response accuracy, and latency. • Stay up-to-date with the latest advancements in NLP, LLMs, and speech technologies. ⸻ Required Skills and Qualifications: • Proven experience in building voice agents or voice-based applications using LLMs. • Proficiency in Python, Node.js, or a similar programming language for backend development. • Strong understanding of Natural Language Processing (NLP) and Natural Language Understanding (NLU). • Hands-on experience with LLMs (OpenAI GPT, GPT-4, GPT-4-turbo, or similar). • Expertise in Text-to-Speech (TTS) systems (e.g., Eleven Labs, Google TTS). • Proficiency with Speech Recognition APIs (e.g., Whisper, Google Speech API). • Experience in deploying and scaling voice agents on cloud platforms (AWS, GCP, Azure). • Familiarity with WebSocket, RESTful APIs, and real-time communication protocols. • Strong problem-solving and debugging skills. • Excellent communication and teamwork skills. ⸻ Preferred Qualifications: • Experience with real-time voice interaction applications. • Familiarity with voice modulation and voice character customization. • Previous experience with voice-based customer support systems. • Knowledge of Docker, Kubernetes, and cloud-based deployment. Show more Show less