AI Engineer |Gen AI (healthcare Domain)_Hybrid@Denver(CO)

Job title: AI Engineer |Gen AI (healthcare Domain)

Work Location: Denver(CO)

Hybrid

Minimum years of experience: 8 TO 10

Role Overview:
We are looking for a Senior AI / GenAI Engineer with strong experience in production-grade ML systems, Generative AI (LLMs, RAG, Agents), and enterprise automation. The ideal candidate will have hands-on expertise in deploying scalable AI systems, ensuring reliability, monitoring, and governance, and working across domains such as healthcare or enterprise IT operations.
Key Responsibilities: 1. GenAI & LLM Engineering
Design and implement RAG pipelines using vector stores (Pinecone, FAISS, etc.) Build and deploy LLM-based applications using OpenAI, Claude, LLaMA, or similar Develop multi-agent systems (LangChain, LangGraph, CrewAI, Autogen) Optimize prompts, retrieval strategies, and model performance for production use
2. ML Engineering & Data Science
Build and deploy ML models across:
Classification, Regression, NLP, Time-series, and Anomaly Detection Perform EDA, feature engineering, and experiment design Implement A/B testing frameworks and performance evaluation pipelines
3. MLOps & Productionization
Implement end-to-end ML lifecycle:
Model training, testing, deployment, monitoring, and rollback Use tools like MLflow, CI/CD pipelines (GitHub Actions/Azure DevOps) Ensure model versioning, reproducibility, and governance Manage online & batch inference systems
4. Observability & Reliability
Build monitoring systems for:
Model drift
Performance degradation
Hallucination detection in LLMs
Define incident response and rollback strategies Maintain dashboards and alerting frameworks

5. AI Safety & Compliance
Implement AI guardrails:
PII/PHI detection
Content filtering
Prompt injection defense
Ensure compliance with regulatory standards (e.g., HIPAA) 6. Cloud & Infrastructure

Deploy solutions on AWS, Google Cloud Platform, or Azure
AWS Bedrock, SageMaker
Google Cloud Platform Vertex AI
Azure OpenAI / AI Foundry
Build scalable infra using Docker, Kubernetes, Terraform 7. Enterprise Automation (RPA Integration)

Design and support RPA workflows using Automation Anywhere / UiPath Integrate AI/ML models into automation pipelines Manage bot lifecycle, orchestration, and governance 8. Collaboration & Leadership

Work with product, data, and engineering teams to deliver scalable solutions Mentor junior engineers and review technical designs Create documentation (PDDs, SDDs, architecture designs) Required Skills
Core Technical Skills:
Strong Python development (FastAPI, ML libraries) ML frameworks: PyTorch / TensorFlow / Scikit-learn GenAI stack: OpenAI, Claude, LLaMA, Hugging Face RAG systems and vector databases (Pinecone, FAISS, etc.) MLOps & Systems

MLflow, model registry, CI/CD pipelines
Experiment tracking and automated testing Deployment patterns (batch + real-time inference) Data & APIs

SQL, REST/SOAP APIs
Experience with enterprise systems (SAP, Salesforce, etc. is a plus)
Nice to Have:
Healthcare domain experience (HIPAA compliance, clinical or claims data) Experience with agentic workflows & human-in-the-loop systems Hands-on experience in cost optimization for LLM workloads RPA certifications (Automation Anywhere / UiPath)