Trusting Social

Tóm tắt công việc

The Machine Learning Engineering team is at the forefront of our efforts to develop and deploy     cutting-edge conversational AI systems powered by multi-agent architectures and large language models (LLM). We work closely with our research team to optimize, scale, and innovate the deployment of our state-of-the-art models, ensuring that our conversational AI systems are efficient, scalable, and capable of handling complex, multi-turn interactions with human-like fluency.

As a Senior Machine Learning Engineer focused on multi-agent systems, you will lead efforts to optimize, scale, and re-architect our conversational AI models. You'll be responsible for designing and implementing advanced systems that enable multiple agents to collaborate seamlessly, providing intelligent and coherent responses. A key focus of your role will be to enhance our voice agents to support complex workflows and handle interactions as smoothly as a human would, including interrupt handling and end-turn detection in a noise environment.

Responsibilities

• Lead the re-architecture of our voice agent systems to support complex workflows, ensuring flexibility and scalability.
• Develop and implement advanced techniques for interrupt handling and end-turn detection in voice interactions, mimicking human-like conversation flow.
• Collaborate with cross-functional teams to design and implement multi-agent systems that can handle a wide range of applications, from customer support to domain-specific voice agent.
• Lead the integration of advanced speech-to-text and text-to-speech capabilities into our conversational AI systems, enabling seamless and natural voice-based interactions.
• Mentor junior team members and contribute to setting technical direction for the team.
• Stay at the forefront of advancements in machine learning optimization, model serving technologies, and conversational AI, and drive their adoption within the organization.

• Bachelor/Master's in Computer Science, Electrical Engineering, or a related field, with a focus on machine learning or artificial intelligence.
• 5+ years of hands-on experience in machine learning engineering, with a strong emphasis on model optimization, serving, and system architecture.
• Extensive experience in designing and implementing complex AI systems, particularly in the realm of conversational AI and multi-agent architectures.
• Deep expertise in natural language processing (NLP) techniques and their application in conversational AI.
• Proven track record of optimizing and scaling large language models and multi-agent systems.
• Strong programming skills in Python, with extensive experience in developing and deploying machine learning models in production environments.
• Advanced knowledge of asynchronous programming using Python for handling concurrent and asynchronous operations, particularly in real-time speech processing.
• Experience with LLM serving technologies such as Nvidia TensorRT-LLM, vLLM, or llama.cpp.
• Excellent communication and leadership skills, with the ability to drive technical discussions, mentor team members, and collaborate effectively across departments.

Preferred Qualification

• Experience with voice processing technologies and real-time audio signal processing.
• Familiarity with cloud platforms (AWS, GCP, Azure) for deploying and scaling AI systems.
• Contributions to open-source projects or research publications in the field of conversational AI or multi-agent systems.