Senior AI Systems Quality Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior AI Systems Quality Engineer based in United States.

This role focuses on engineering quality, reliability, and trust into production-grade AI systems used in mission-critical healthcare environments. You will design automated testing frameworks, evaluation pipelines, and scalable quality practices for agentic and LLM-driven applications. The position goes beyond traditional QA, emphasizing quality-by-design, safe failure behavior, measurable evaluation signals, and continuous validation throughout the development lifecycle. You will help build an AI testing platform integrated with Databricks and MLflow to support traceability, lineage, and auditability at scale. Working closely with AI engineering, platform, security, and delivery teams, you will influence release readiness and operational confidence. This is an automation-first engineering opportunity for someone passionate about making advanced AI systems reliable, governed, and production-ready.

Accountabilities:

• Build and deploy production-grade automated validation frameworks, test harnesses, and evaluation pipelines across the full AI development lifecycle.
• Design and evolve an AI testing platform integrated with Databricks and MLflow to enable repeatable testing, traceability, lineage, and auditability.
• Create large-scale, scenario-based test suites covering hundreds or thousands of cases, including edge cases, long-tail scenarios, and system failure modes.
• Validate agentic orchestration behaviors such as tool usage, memory, decision logic, and non-deterministic outputs before production deployment.
• Embed quality-by-design principles by defining system contracts, guardrails, safe-degradation patterns, and validation requirements at key system boundaries.
• Define measurable quality signals for LLM systems, including grounding, hallucination rates, relevance, latency, cost, accuracy, and explainability.
• Integrate automated quality gates into CI/CD pipelines and ensure validation runs continuously following model, prompt, or code changes.
• Build reusable testing libraries, frameworks, and components that enable engineering teams to adopt consistent AI quality practices.
• Establish measurable release-readiness criteria and support go/no-go decisions based on defined quality thresholds.
• Partner with AI, platform, security, and delivery teams to translate business and mission requirements into clear quality criteria, trade-offs, and confidence levels.
• Evaluate system behavior, reliability, security, privacy, and operational risk in regulated and mission-critical environments.

Requirements:

• 7+ years of software engineering experience, primarily focused on backend or platform systems.
• Proven experience designing and implementing automated AI testing and validation solutions in production environments.
• Demonstrated ability to build custom testing, validation, or evaluation frameworks for complex and distributed systems.
• Strong proficiency in Python and/or TypeScript within modern AI engineering environments.
• Hands-on experience with AI-powered systems, including LLM-based or agentic workflows and non-deterministic behavior.
• Experience designing AI testing at scale, including regression frameworks, long-tail evaluations, and broad test coverage.
• Deep understanding of CI/CD practices and experience embedding automated tests and quality gates into deployment pipelines.
• Solid knowledge of AWS cloud-native architectures.
• Strong track record of engineering for quality, reliability, governance, safety, and operational resilience as core system principles.
• Working knowledge of security, privacy, and operational risk within regulated or mission-critical environments, including failure modes and recovery strategies.
• Experience with AI testing methodologies such as non-deterministic output evaluation, drift detection, bias and fairness testing, and robust regression strategies.
• Ability to establish measurable trust thresholds and operationalize metrics such as query accuracy, hallucination limits, explainability, and PHI-safe behavior as release criteria.
• Experience collaborating with domain experts to define correctness and real-world validation scenarios that reflect genuine production use cases.
• Experience with Databricks and Medallion architecture is preferred but not requir…