Remote ML Engineer – Real-Time Voice AI & Edge Inference

MobDial; United States; Remote; USD 120,000 - 180,000; Full time

Benefits offered by this job

Remote work

Job summary

MobDial is seeking an ML engineer to develop and deploy machine learning for real-time voice applications, combining speech processing with production engineering. The role includes detecting answering machines, analyzing speech and sentiment, and integrating models into a live dialing pipeline.

You will train and deploy detection models with latency targets, build transcription and sentiment pipelines, and optimize inference for edge deployment on serverless functions, collaborating with

Qualifications

• At least three years of ML engineering experience including production model deployment.
• Experience processing speech or audio (ASR, TTS, or speaker diarization).
• Proficiency in Python and familiarity with TypeScript.
• Knowledge of model serving tools such as ONNX or TensorRT.

Responsibilities

• Train and deploy answering machine detection models, targeting p99 latency below 3,500 milliseconds.
• Build real-time transcription and sentiment analysis pipelines.
• Develop call-quality scoring models using measures such as MOS and jitter.
• Optimize model inference for edge deployment on serverless functions.
• Work with the platform team to integrate ML capabilities into the dialing pipeline.

Skills

Python

TypeScript

Production ML deployment

Tools

ONNX

TensorRT

Job description

MobDial is seeking an ML engineer to develop and deploy machine learning for real-time voice applications, combining speech processing with production engineering. The role includes detecting answering machines, analyzing speech and sentiment, and integrating models into a live dialing pipeline.

You will train and deploy detection models with latency targets, build transcription and sentiment pipelines, and optimize inference for edge deployment on serverless functions, collaborating with