AI Engineer & Researcher, Inference - Salt Lake City, USA

About Speechify

Speechify is an AI-powered solutions company focused on delivering high-quality speech technologies. We build scalable models and tools to enable natural, efficient text-to-speech experiences across platforms.

Role: AI Engineer & Researcher, Inference

Location: Salt Lake City

Responsibilities

• Design, implement, and optimize inference pipelines for speech models, ensuring low latency and high accuracy.
• Research and prototype novel inference techniques, model compression, and deployment strategies for production systems.
• Collaborate with product and research teams to translate requirements into robust, scalable solutions.
• Evaluate model performance, conduct ablation studies, and monitor metrics in live environments.
• Contribute to code quality, testing, and documentation; mentor junior engineers as needed.

Qualifications

• Strong background in machine learning, deep learning, and statistical methods.
• Experience with Python and ML frameworks (e.g., PyTorch, TensorFlow).
• Hands-on experience with inference engines and optimization toolchains (e.g., TensorRT, ONNX Runtime).
• Familiarity with GPU programming (CUDA) and distributed systems.
• PhD or MS in CS, EE, or related field preferred; equivalent practical experience considered.
• Excellent problem solving and communication skills; ability to work cross-functionally.

Nice-to-have

• Experience with speech synthesis or TTS systems, linguistics, or audio processing.
• Experience with on-device inference and mobile platforms.

Benefits

• Competitive salary and equity package
• Health, dental, and vision insurance
• Flexible work arrangements and focus on work-life balance
• 401(k) with company matching
• Opportunities for professional growth and impact in AI-driven products