Senior AI/ML Engineer - Remote AI Ops & Deployment

INSPYR Solutions; Brentwood (TN); Remote; USD 96,000 - 110,000; Full time

Benefits offered by this job

Flexible remote work opportunities

Professional development programs

Employee wellbeing culture

Job summary

INSPYR Solutions is seeking an AI/ML Engineer to serve as the primary technical resource for production generative AI and ML operations. This role combines LLM gateway and retrieval support with model deployment, inference, evaluation and pipeline operations in a remote capacity.

The position requires production experience in both generative AI and traditional ML, with strong troubleshooting and prioritization skills.

Qualifications

• Demonstrated production support across generative AI and ML pipelines.
• Hands-on LLM API integration and gateway troubleshooting.

Responsibilities

• Provide Level 2/3 support through ServiceNow, diagnose incidents and document root causes.
• Troubleshoot LLM gateways, authentication, quotas, and timeouts; trace failures across APIs.
• Operate RAG and Azure AI Search workflows; investigate indexing and data quality issues.
• Support Databricks model processing, evaluation jobs and inference; resolve runtime issues.
• Maintain evaluation datasets and checks for retrieval relevance and model quality.
• Monitor availability, latency, and token usage; correlate logs to diagnose failures.
• Version code, prompts, configurations and artifacts; maintain CI/CD release procedures.

Skills

Production support

Incident response

Troubleshooting

Python

SQL

Communication of findings

Tools

Azure Foundry/Azure OpenAI

Azure AI Search

Databricks

Snowflake

AKS

Azure App Service

CI/CD

Job description

INSPYR Solutions is seeking an AI/ML Engineer to serve as the primary technical resource for production generative AI and ML operations. This role combines LLM gateway and retrieval support with model deployment, inference, evaluation and pipeline operations in a remote capacity.

The position requires production experience in both generative AI and traditional ML, with strong troubleshooting and prioritization skills.