Senior AI Engineer – LLM Apps, Hybrid, High-Impact

MediaAlpha; Bellevue (WA); Hybrid; USD 150,000 - 210,000; Full time

Benefits offered by this job

Annual bonus program

Employer-paid health, dental, vision

401(k) with matching

Open PTO + 13 holidays + 5 recharge

LinkedIn Learning reimbursement

Wellness & internet stipend

Parental leave (22w primary, 12w other

Dog-friendly offices

Pet adoption reimbursement

Job summary

MediaAlpha, a data-driven ad-tech company, seeks a Senior Applied AI Engineer to build and deploy end-to-end LLM-powered features. You will design MCP servers, implement RAG pipelines, and integrate AI services into products and internal tools.

The role emphasizes close collaboration with engineers, product and business stakeholders, delivering high-quality, scalable AI capabilities and championing best practices in coding, testing, and deployment.

Qualifications

• Minimum 5 years in software development with AI feature delivery.
• B.S. in CS or technical field required.
• Strong programming, testing, and deployment practices.

Responsibilities

• Own end-to-end development of LLM-powered features from integration to production.
• Design MCP servers exposing data/tools to LLM applications.
• Build and maintain retrieval-augmented generation pipelines.
• Integrate LLM services into MediaAlpha products and tools.
• Develop and iterate prompts; test and evaluate quality.
• Support live AI features in production and ensure reliability.
• Promote coding excellence and robust testing practices.
• Collaborate with engineers, product, and stakeholders on features.

Skills

LLM expertise

Python

Software engineering

SQL skills

Cloud AWS

API integration

Prompt engineering

Stakeholder communication

Education

B.S. in CS or related

Tools

MCP servers

RAG pipelines

Vector search

Function calling

Agent orchestration

Job description

MediaAlpha, a data-driven ad-tech company, seeks a Senior Applied AI Engineer to build and deploy end-to-end LLM-powered features. You will design MCP servers, implement RAG pipelines, and integrate AI services into products and internal tools.

The role emphasizes close collaboration with engineers, product and business stakeholders, delivering high-quality, scalable AI capabilities and championing best practices in coding, testing, and deployment.