Senior Applied AI Engineer: Real-Time Voice & LLM

amchealth; Austin (TX); On-site; USD 150,000 - 230,000; Full time

Job summary

AMC Health in the United States is seeking a Senior Software Engineer to build and operate production AI voice agents and ML systems in a regulated healthcare setting. You will own end-to-end real-time voice pipelines, LLM-based components, and traditional ML workflows, with a strong emphasis on reliability, latency, security, and scalable cloud architecture.

This role spans real-time systems, LLM engineering, and cloud infrastructure, demanding practical judgment about when to use models and

Qualifications

• 7+ years building and operating production backend systems; Python proficiency.
• Experience running distributed systems in the cloud; telemetry to root cause debugging.
• Hands-on production experience with LLMs or generative AI.
• Fluent across the traditional ML lifecycle; productionize, not just research.
• Disciplined in a regulated environment with careful handling of sensitive data.

Responsibilities

• Ship and debug code on a live, real-time voice pipeline where latency and correctness are user-facing.
• Design control systems around LLMs: guardrails, budgets, watchdogs, safe fallbacks.
• Build and operate LLM evaluation and batch-analysis pipelines.
• Own traditional ML workflows from data to scheduled production inference.
• Trace production issues from a metric anomaly to root cause.

Skills

Python

Distributed systems

LLMs / Generative AI

ML lifecycle

AWS

Regulated environment

Telemetry / debugging

Job description

AMC Health in the United States is seeking a Senior Software Engineer to build and operate production AI voice agents and ML systems in a regulated healthcare setting. You will own end-to-end real-time voice pipelines, LLM-based components, and traditional ML workflows, with a strong emphasis on reliability, latency, security, and scalable cloud architecture.

This role spans real-time systems, LLM engineering, and cloud infrastructure, demanding practical judgment about when to use models and