Apply on Employer Site

Codoxo · 3 weeks ago

Senior Machine Learning AI Engineer- Healthcare Payment Integrity

United States

Full-time

Remote

Senior Level

5+ years exp

Codoxo is the premier provider of artificial intelligence-driven solutions and services that help healthcare companies and agencies proactively detect and reduce risks from fraud, waste, and abuse. The Senior Machine Learning AI Engineer will architect, build, and operate Codoxo’s next‑generation AutoML Platform, focusing on model training, optimization, deployment, and continuous improvement across healthcare claims.

AnalyticsArtificial Intelligence (AI)Fraud DetectionGenerative AIHealth CareMachine LearningSoftware

Growth Opportunities

No H1B

Responsibilities

Lead the design and build-out of Codoxo’s AutoML Platform as a flagship engineering initiative — creating a scalable, automated, and customer‑isolated system for model training, feature engineering, hyperparameter optimization, and evaluation

Architect Codoxo’s Model‑as‑a‑Service (MaaS) layer on AWS (SageMaker, Django, Batch, ECS/EKS, API Gateway) to deploy secure, high‑performance inference endpoints across single‑tenant environments

Develop production‑grade MLOps pipelines including CI/CD for ML, automated approvals, model lineage, auditability, and monitoring

Implement automated retraining pipelines triggered by drift detection, new data arrival, or scheduled intervals

Build observability for model health, drift, inference latency, cost efficiency, and cross‑customer performance using CloudWatch and Model Monitor

Create reusable feature pipelines and experimentation environments to accelerate Data Science productivity

Leverage our model performance and code utilization dashboards to automate model regeneration using Claude Code and seamlessly retire outdated models in favor of more relevant replacements

Ensure all ML components meet Codoxo’s HITRUST, NIST 800‑53, and FedRAMP requirements

Qualification

AWS ML/AI stackPython engineeringMLOps toolingAutoML systems designGPU trainingModel explainabilityTerraform experienceFastAPI experienceDjango experienceFlask experienceData Science experienceLLM development

Required

5+ years building and operating ML or data platforms in production environments

Expertise in AWS ML/AI stack: SageMaker, Lambda, Django, Batch, EMR, ECR, ECS/EKS, Step Functions, CloudWatch, EventBridge, S3

Strong Python engineering skills for ML pipelines, infrastructure, and automation. Familiarity with LLM coding solution is a must (e.g. Claude Code, Cursor, Windsurf, Google Gemini Code Assist, AWS Q Code Developer, etc.)

Experience designing AutoML systems, hyperparameter optimization workflows, or large-scale training infrastructure

Hands-on experience with MLOps tooling such as MLflow, SageMaker Pipelines, or Kubeflow

Deep understanding of secure architecture patterns in single-tenant AWS environments (KMS, IAM, VPC isolation)

Previous experience in Data Science and LLM development

GPU training or inference experience

Model explainability, fairness, or responsible AI frameworks

Terraform, CDK, or Pulumi experience

FastAPI/Django/Flask experience for AI microservices