Senior AI/ML Engineer: Build Production-Grade AI Agents

IMO Health; Houston (TX); On-site; USD 150,000 - 200,000; Full time

Job summary

IMO Health is seeking a Senior AI/ML Engineer to design, build, deploy, and evolve AI models and agent workflows for clinical terminology and content operations. The role combines development with production ownership, guiding models and agents from experimentation to reliable production use.

The ideal candidate has hands-on experience with LLMs, retrieval-augmented generation, vector databases, and enterprise governance, plus strong Python and cloud skills.

Qualifications

• 5+ years of AI/ML engineering or related field.
• Hands-on experience building agents and agentic workflows.
• Experience building RAG solutions, embeddings, vector databases, semantic search.
• MLOps experience for production deployment and CI/CD across environments.
• Strong Python proficiency and API/pipeline development.
• Experience with cloud-based AI infrastructure (AWS Bedrock).
• Strong troubleshooting and root-cause analysis with cross-functional partners.
• Clear written and verbal communication in cross-functional teams.

Responsibilities

• Develop ML models, agents, and automation workflows for terminology management and content production.
• Build agentic workflows using LLMs, tools, APIs, knowledge sources, and rules.
• Develop retrieval-augmented generation and search capabilities.
• Collaborate with data science to productionize existing agents and integrate your models.
• Own deployment, monitoring, and remediation of AI workflows in production.

Skills

AI/ML engineering

Agent workflows

RAG solutions

MLOps

Python

SQL/PostgreSQL

AWS Bedrock

Troubleshooting

communication

Tools

LangChain

LangGraph

LlamaIndex

OpenSearch

Vector databases

Job description

IMO Health is seeking a Senior AI/ML Engineer to design, build, deploy, and evolve AI models and agent workflows for clinical terminology and content operations. The role combines development with production ownership, guiding models and agents from experimentation to reliable production use.

The ideal candidate has hands-on experience with LLMs, retrieval-augmented generation, vector databases, and enterprise governance, plus strong Python and cloud skills.