Senior Software Engineer, GenAI

Job Description

Senior Software Engineer, GenAI

Austin, Texas (Hybrid)

About Tricentis

Tricentis is a global leader in AI-driven, codeless software testing and quality engineering, empowering enterprises to accelerate digital transformation while reducing risk.

Trusted by over 3,000 customers—including organizations like T-Mobile and Allianz—Tricentis delivers innovative solutions such as Tosca, qTest, Testim, and SAP Test Automation to enable continuous, intelligent testing at scale.

Our mission is to redefine how software quality is achieved by leveraging AI, model-based testing, and codeless automation to make testing faster, smarter, and more accessible.

About the Role

We are looking for a Senior Engineer to drive the next generation of AI-powered testing and quality engineering solutions across the Tricentis product portfolio.

In this role, you will help shape how AI transforms software testing—from intelligent test generation and impact analysis to autonomous validation systems.

You’ll act as both a technical leader and hands-on builder, working across teams to deliver scalable AI systems embedded into products like Tosca, qTest, and Testim.

Key Responsibilities

Technical Contribution & Collaboration


* Contribute to AI-focused engineering initiatives, delivering high-quality implementations aligned with team direction using Spec driven development.


* Participate in architecture and development of AI-driven testing capabilities.


* Share knowledge through code reviews, design discussions, and team collaboration.


* Make sound engineering decisions balancing performance, cost, scalability, and customer value.


* Collaborate with Product Management and Design to translate customer needs into AI-powered features.


* Contribute to internal knowledge sharing around AI.

AI Implementation & Quality


* Design and implement LLM-powered solutions for the next generation of software quality solutions.


* Participate in experimentation efforts to validate new AI-driven testing approaches.


* Contribute to testing strategies for AI systems, including: Model evaluation and benchmarking, Regression detection for AI behaviors, and Reliability and explainability validation


* Ensure high-quality implementation through code reviews and adherence to best practices.


* Partner with domain experts in enterprise ecosystems (e.g., SAP) to optimize testing solutions for complex business applications.


* Contribute to improvements in DevOps integration and continuous testing pipelines.

Required Qualifications

Technical Expertise


* 4+ years of demonstrated work experience building production-grade software using Python.


* 3+ years of experience designing and deploying AI/ML or LLM-based solutions in production.


* Hands-on experience with AI coding assistants (GitHub Copilot, Cursor, Claude Code, etc.).


* Strong knowledge of:
+ Generative AI and LLM ecosystems...