Applied ML Engineer

Knowtex; United States; On-site; USD 120,000 - 160,000; Full time

Job summary

Knowtex is building the future of voice AI operating systems for clinicians, transforming how healthcare documentation happens at the point of care. We seek an Applied ML Engineer to productionize and scale machine learning systems powering our voice AI platform.

You will collaborate with ML Scientists and Platform teams to optimize inference, deploy models in regulated healthcare environments, and build robust evaluation and monitoring pipelines to ensure low latency and high reliability in

Qualifications

• 3–7+ years of experience in ML engineering or Applied ML roles.
• Strong Python and PyTorch (or TensorFlow) skills.
• Experience deploying ML models in production environments.
• Familiarity with transformer architectures and large language models.
• Experience with model optimization techniques like quantization, distillation, pruning.
• Experience with cloud infrastructure (AWS preferred).
• Strong software engineering fundamentals and debugging skills.

Responsibilities

• Productionize ML models for real-time clinical applications.
• Optimize inference pipelines for low latency and high throughput.
• Deploy and scale models using AWS-based infrastructure.
• Build automated evaluation and regression testing frameworks for LLM outputs.
• Implement monitoring systems for model performance and drift detection.
• Collaborate with Backend teams to integrate ML services into APIs and workflows.
• Improve model efficiency through quantization, batching, caching, and optimization techniques.
• Support specialty-level model evaluation and performance analysis.
• Contribute to CI/CD workflows for ML deployment.

Skills

Python

PyTorch

TensorFlow

Production ML deployment

Transformer models

Cloud (AWS)

Software debugging

Tools

SageMaker

Triton Inference Server

CI/CD for ML

AWS

Job description

About Knowtex

Knowtex is building the future of voice AI operating systems for clinicians, transforming how healthcare documentation happens at the point of care. Founded by Stanford AI scientists with deep clinical experience, we're experiencing explosive growth across both commercial health systems and federal healthcare, with our ambient documentation platform scaling rapidly to thousands of clinicians across hundreds of specialties. We're at an inflection point where cutting‑edge AI meets real clinical impact, giving clinicians hours back each day to focus on what matters most - their patients.

Position Overview

We are seeking an Applied ML Engineer to productionize and scale machine learning systems powering our voice AI platform. This role bridges research and engineering — transforming models into reliable, low-latency, production-grade systems deployed across enterprise healthcare environments.

You will work closely with ML Scientists, Backend Engineers, and Platform teams to optimize inference performance, build evaluation pipelines, and ensure robust model deployment in regulated environments.

Key Responsibilities

• Productionize ML models for real-time clinical applications
• Optimize inference pipelines for low latency and high throughput
• Deploy and scale models using AWS-based infrastructure
• Build automated evaluation and regression testing frameworks for LLM outputs
• Implement monitoring systems for model performance and drift detection
• Collaborate with Backend teams to integrate ML services into APIs and workflows
• Improve model efficiency through quantization, batching, caching, and optimization techniques
  Support specialty-level model evaluation and performance analysis
• Contribute to CI/CD workflows for ML deployment

Required Qualifications

• 3-7+ years of experience in machine learning engineering or applied ML roles
• Strong proficiency in Python and PyTorch (or TensorFlow)
• Experience deploying ML models in production environments
• Familiarity with transformer architectures and large language models
• Experience with model optimization techniques (quantization, distillation, pruning)
• Experience working with cloud infrastructure (AWS preferred)
• Strong software engineering fundamentals and debugging skills

Preferred Qualifications

• Experience with speech recognition systems or NLP pipelines
• Experience with Triton Inference Server or similar deployment frameworks
• Familiarity with healthcare data or clinical documentation workflows
• Experience working in regulated environments (HIPAA, GovCloud, etc.)
• Knowledge of medical coding systems (ICD-10, CPT)

Technical Environment

• Python, PyTorch / TensorFlow
• Transformer-based LLM architectures
• AWS (SageMaker, ECS, Lambda, S3)
• Triton Inference Server
• CI/CD pipelines for ML deployment
• Observability tools for performance and drift monitoring

Compensation & Benefits

• Meaningful equity compensation
• Unlimited PTO
• Premium health, dental, and vision coverage
• 401(k) plan