Research Engineer, Audio and Speech

The role

You will build models and agent harnesses for real-time voice agents. You will research and train multimodal and full-duplex models to advance conversational AI.

What you will do

• Design and build agent harnesses optimized for streaming speech, turn-taking, interruptions, overlapping speech, and continuous interaction
• Research and train multimodal and full-duplex models that jointly understand audio, reason, and generate speech
• Improve speech recognition, voice activity detection, endpointing, and speech generation
• Build evaluations and use production calls to ship improvements in accuracy, latency, naturalness, and task outcomes
• Optimize end-to-end inference for responsiveness, throughput, stability, and cost

Required qualifications

• 2+ years of experience in speech, audio ML, multimodal ML, or production machine learning
• Experience developing or adapting autoregressive, diffusion, flow-matching, or codec-based speech models
• Hands-on experience with streaming agent systems, low-latency inference, production model serving, and evaluation on real-world audio
• Fluency in Python
• Experience with a modern deep-learning framework such as PyTorch
• Strong foundations in machine learning and signal processing
• A track record of taking research ideas from prototype to reliable, measurable production impact

Nice to have

• Familiarity with speech-to-speech or full-duplex models
• Experience with telephony, multilingual speech, noisy-channel robustness, speaker adaptation, or expressive speech generation

Benefits

• Medical, Dental, and Vision benefits for you and your family
• Life Insurance and Disability Benefits
• Retirement Plan (e.g., 401K, pension)
• Parental Leave
• Fertility and family building benefits through Carrot
• Monthly stipend to support your wellness, lifestyle, and work-life balance
• Daily lunches and snacks in the office
• Take what you need vacation policy

About the company

Decagon is a conversational AI platform that enables enterprises to deploy AI agents across voice, chat, email, and SMS. It is an in-office company driven by values like Just Get It Done and The Polymath Principle.