Senior Applied AI Software Engineer

Hybrid role: 3 days/week in office

Role Overview

As a Senior Applied AI Engineer at MediaAlpha, you will be a key contributor building LLM-powered applications for our internal teams and ad serving platform. You will implement features end-to-end: integration, deployment, and operational health. You will work alongside engineering, product, and business stakeholders to deliver features that solve real business problems.

The ideal candidate is a strong software engineer with hands-on experience building LLM-powered features in production, who works well across organizational boundaries and improves the conditions of any area they are in. We are an intentionally small organization, designed for agility, speed, and workability.

Responsibilities

• Own the full software development lifecycle of implementing LLM-powered features, from integration through production deployment and operational health.
• Design and build MCP (Model Context Protocol) servers that expose internal data and tools to LLM applications.
• Design, implement, and maintain retrieval-augmented generation (RAG) pipelines, including vector search, tool-use patterns, and multi-step agent workflows.
• Integrate LLM-based services into MediaAlpha's products, internal tools, and data ecosystem.
• Write and iterate on prompts, and build the harnesses needed to test and evaluate them.
• Be part of the team that maintains and supports our live production AI features.
• Be a champion of instilling excellence in coding, testing, and quality into the team and culture.
• Work directly with stakeholders in defining product capabilities and developing and testing new features and integrations.

Requirements

• Minimum of 5 years of experience in software development.
• B.S. required, preferably in a technical discipline (e.g., computer science).
• Strong programming skills, including software engineering methodologies and best practices.
• Strong SQL skills and understanding of database and query optimizations.
• Hands-on experience building LLM-powered features in production.
• Familiarity with common AI implementation patterns: MCP server design, RAG, vector search, function calling/tool use, agent orchestration, and structured output extraction.
• Practical prompt engineering skills with demonstrated ability to iterate and evaluate quality.
• Experience integrating with APIs and building services that call external or internal LLM endpoints.
• Familiarity with cloud environments (AWS preferred: EC2, S3, Bedrock).
• Ability to work independently with minimal supervision.
• A self-starter, comfortable with ambiguity and ability to problem solve while paying careful attention to detail.
• Experience working with engineers and non-technical stakeholders.
• Ability to articulate and communicate clearly, concisely, and thoughtfully.

Compensation & Benefits

We are excited to offer a total base compensation of $150,000 to $210,000 per year for this position based on experience and qualifications. But that's not all - as a valued member of our team, you will also have access to an array of top-notch benefits, including:

• Annual bonus program and participation in our Restricted Stock Unit program
• 100% Employer-paid health, dental, and vision insurance for you, your dependents, and spouse or registered domestic partner
• 100% Employer paid long term disability, and life insurance
• 401(k) retirement plan with matching contributions to help you plan for your future
• Open Paid Time Off policy with a Birthday Hookie day off, 13 holidays, and 5 Recharge days
• Professional development reimbursement along with a subscription to LinkedIn Learning 
• Cell Phone, Wellness, and Internet expense reimbursement, along with a subscription to the Calm App
• 100% fully paid parental leave for team members up to 22 weeks for the primary caregiver and 12 weeks for the secondary caregiver 
• Dog-friendly offices (LA and AZ) along with a $300 pet adoption reimbursement