Staff Applied AI Engineer - Platform & Client Impact

Aimlroles; Northern (KY); Hybrid; USD 158,000 - 248,000; Full time

Job summary

Addepar's Applied AI team embeds with strategic clients to identify where AI can transform workflows, prototype capabilities, prove they work, and partner with core engineering to ship them as products for all customers.

As a Staff Applied AI Engineer, you’ll set the technical direction for agents and evaluation, own production readiness decisions, build reusable patterns, mentor engineers, and translate client learnings into roadmap priorities.

Qualifications

• 6+ years of professional software engineering experience.
• Proven experience with Python as the team’s primary language.
• Deep experience building and operating AI/LLM-powered systems in production.

Responsibilities

• Set the technical direction for AI engineering across the team: agent architecture patterns, evaluation methodology, deployment and monitoring strategies.
• Design the AI platform layer, including shared agent frameworks and evaluation infrastructure.
• Work directly with clients on complex engagements to design AI capabilities for unautomated workflows.
• Make high-judgment calls on production readiness and balance speed with reliability.
• Drive the handoff from prototype to product and generalize client capabilities.
• Lead production quality for AI systems with observability and SLOs.
• Mentor and grow AI and full-stack engineers.

Skills

Python

Software engineering

AI/LLM systems

Agent architectures

Production systems

Customer engagements

Communication skills

Education

BS/MS in Computer Science or Mathematics or equivalent

Tools

Claude Code

Codex

Job description

Addepar's Applied AI team embeds with strategic clients to identify where AI can transform workflows, prototype capabilities, prove they work, and partner with core engineering to ship them as products for all customers.

As a Staff Applied AI Engineer, you’ll set the technical direction for agents and evaluation, own production readiness decisions, build reusable patterns, mentor engineers, and translate client learnings into roadmap priorities.