Senior AI Software Developer in Test

Caseware is one of Canada's original Fintech companies, having led the global audit and accounting software industry for over 30 years, with more than 500,000 users across 130 countries and available in 16 different languages. While you might not have heard of us (yet) over 36,000 accounting and audit professionals list Caseware as a skill on their LinkedIn profiles! We are at the forefront of AI adoption in our cloud-native SaaS platform, building intelligent, agentic features that transform how users interact with our product. As an AI SDET, you'll pioneer and scale AI-driven testing practices from the ground up—fast-tracking reliable, safe, and high-performing AI capabilities across the organization. You will contribute in areas to reduce deployment risks, minimize hallucinations and drift, ensure ethical AI, and drive faster releases (targeting 20-40% velocity gains through automated validations). This is a high-impact, foundational role in Platform Engineering's Quality function, where your work will directly influence product trust, compliance, and innovation for our end users.  📍 Location: This is a fully remote position located in Colombia.  You will be reporting to: Jai Joshi Contact: Maira Russo - Senior Talent Acquisition Partner What You’ll Be Doing

Quality & AI-First Mindset 

Evolve a modern, AI-first quality strategy for our fast-scaling SaaS architecture, including foundational infrastructure and emerging agentic/intelligent systems. 

Integrate AI enhancements into CI/CD pipelines (e.g., predictive flakiness detection, automated test generation, self-healing scripts) to improve isolation, data setup, & execution reliability using existing/suggesting tools. 

Establish scalable testing practices that support hyper-growth and petabyte-scale AI data pipelines. 

AI-Focused Test Strategy, Automation & Evaluation 

Design deterministic and statistical testing approaches for non-deterministic LLM-based and agentic systems, addressing hallucinations, prompt injection, bias, drift, and safety risks. 

Build automated evaluation pipelines and harnesses for correctness, faithfulness, retrieval quality, generation accuracy, tool-calling, planning sequences, and multi-agent flows. 

Execute/Develop test frameworks for the full AI lifecycle: prompts, datasets, embeddings, model versions, RAG pipelines (end-to-end validation), and guardrails. 

Implement red-teaming, bias/fairness checks, and compliance mechanisms; leverage in trend frameworks for metrics and observability. 

Integrate AI-specific quality signals into CI/CD for automated gating and continuous monitoring. 

Cross-Functional & End-to-End Testing 

Partner closely with product, data science, AI engineering, and dev teams to test AI features, conduct multi-agent simulations, and ensure high-quality roadmap delivery. 

Facilitate knowledge sharing and upskilling on AI testing best practices across the Quality Function. 

Metrics, Observability & Continuous Improvement 

Drive core metrics (DORA, test coverage/effectiveness) plus AI-specific indicators (e.g., hallucination rate, context precision, drift detection). 

Build real-time dashboards and support A/B testing of models with post-deployment monitoring. 

Culture, Mentorship & Innovation 

Champion a quality-first, ethical AI mindset organization-wide. 

Mentor SDET’s, lead workshops on AI risks/validation, and influence design/deploy/incident processes. 

As a foundational hire, define roadmaps and best practices for sustainable AI quality assurance. 

Challenges You'll Tackle

Ensuring reliability in agentic systems amid data drift and non-deterministic behavior. 

Scaling tests for global SaaS while maintaining low hallucination rates and strong safety guardrails. 

Building evaluation from scratch in a rapidly evolving landscape (e.g., multi-modal, agentic flows). 

Success in the First 6 Months

Launch foundational AI test frameworks and pipelines, achieving 80-90% coverage for key AI components. 

Reduce AI-related defect escapes by 30-40% and integrate automated safety/compliance checks into all releases. 

Establish metrics dashboards and evaluation loops that enable data-driven iteration on intelligent features. 

What You Will Bring

7+ years in Quality Engineering/SDET roles within cloud-native SaaS environments, including 2+ years hands-on with AI/ML/LLM systems. 

Expertise in automated testing infrastructure, CI/CD (Jenkins/GitHub Actions), and test pyramid strategies (unit → E2E). 

Strong full-stack testing experience (frontend/backend/API) and collaboration with dev teams. 

Proven experience testing LLMs, AI agents, RAG pipelines, and related risks (hallucinations, prompt injection, bias, drift). 

Proficiency in JS/TS, working knowledge of Python or Java; experiance with AI evaluation frameworks (e.g., Ragas, DeepEval, LangChain/LangSmith/LangFuse) and other tools you may have proficiency in. 

Knowledge of performance, Stress and Load testing tools like K6, JMeter, Blazemeter will be nice to have. 

Knowledge of observability (NewRelic), statistical testing methods, red-teaming, and ethical AI practices. 

Excellent communication, and coaching skills; ability to thrive in ambiguity and drive innovation. 

Bachelor's/Master's in Computer Science, AI, or related; certifications (e.g., ISTQB AI Testing) a plus. 

Strong English language communication and collaboration skills