Principal AI Implementation Engineer (Agent Systems)

Life at BriteCore

We take pride in our dynamic, diverse team, unified by shared values of community, integrity, grit and impact. We love what we do and the people we do it with, which is why we welcome every individual, provide them with equal opportunity irrespective of their race, color, national origin, religion, age, gender identity, sexual orientation, veteran, disability or any other legally protected rights that one has.

Click here to learn more about our platform.

Who we are

At BriteCore, we’re a dynamic, forward-thinking company on a mission to empower Property & Casualty (P&C) insurers to grow their business and achieve operational efficiencies with modern cloud-native technology.

Our software platform is mission-critical, enabling carrier customers to manage policies, billing, and claims with an all-in-one core insurance solution that delivers real-time analytics and digital portals for agents and policyholders. While others rely on outdated solutions, we’re leading the shift towards modern cloud technology. With a commitment to continuous innovation, BriteCore delivers new capabilities and enhancements with a flexible and scalable core insurance platform designed to meet the evolving needs of insurers.

We believe in creating an inclusive and collaborative work environment where team members are encouraged to share ideas, challenge the status quo, and grow both personally and professionally. Our distributed team is united by a shared passion for transforming the insurance industry and delivering exceptional service.

Join us at BriteCore and be part of a company that’s shaping the future of insurance technology. You’ll have the opportunity to work with talented individuals and make an impact. Your contributions will make a difference. If you’re ready to create something different, let’s build the future of insurance software together.

Summary

We’re pioneering customer implementation health through intelligent agent design.

At BriteCore, we’re redefining insurance technology implementations with AI-driven agentic systems that ensure flawless customer onboarding. This role focuses on building browser-based semantic agents that emulate stakeholder personas, holistically evaluate implementation health, and accelerate time to value for our customers.

This is a fully remote-based role, however candidates must be located in Argentina or Brazil. This is a long-term Independent Contractor position.

Note: please submit your resume in English.

What you’ll do

Agent Architecture (70%)

• Design stateful agent systems using Python, LangChain, and frameworks for persona emulation
• Build implementation health scoring models that combine technical signals with business outcomes
• Create adaptive validation agents that self-modify based on client-specific configurations

Cross-Functional Impact (30%)

• Partner with implementation teams to codify domain expertise into agentic workflows
• Develop visual dashboards showing real-time implementation progress and risk heatmaps
• Contribute directly to core platform code when agentic solutions require upstream changes

What you’ll bring

• Bachelor’s Degree in Computer Science or a related field
• 7+ years of experience with Python, including Cursor/VS Code AI toolchain mastery
• 5+ years of experience with browser automation (Playwright, Selenium with LLM-driven adapters)
• Proven experience with agentic frameworks (AutoGen, LangGraph, CrewAI)
• Demonstrated expertise in observable architectures (OpenTelemetry, Grafana, Prometheus)
• Excellent verbal and written communication skills, with the ability to thrive in a fast-paced environment

Bonus points

• 2+ years of experience working at a scaling startup
• Familiarity with insurance workflows (P&C, underwriting, claims)

This isn’t traditional QA

• No test scripts: agents develop contextual validation strategies autonomously
• Direct production impact: your systems will actively shape implementation SLAs
• Architectural freedom: build with cutting-edge techniques like: LLM agent swarms, embedding-based health scoring and implementation risk prediction models