• Design, build, and maintain test frameworks, evaluation harnesses, and regression suites for LLM-based agents, covering reasoning quality, tool-call correctness, task completion, and multi-turn coherence.
• Build automated pipelines that run evals and test suites on every model, prompt, or tool-integration change, and integrate them into CI/CD as enforceable quality gates.
• Develop simulators, mocks, and sandbox environments for industrial systems and tool APIs so agents can be tested safely, repeatably, and at scale.
• Implement API, contract, integration, and end-to-end tests for the services, tools, and orchestration layers that agents depend on.
• Develop performance, load, and reliability tests for agent workflows, including failure injection and resilience testing.

Manual and Exploratory Testing

• Perform hands-on exploratory testing of agent behavior, including new capabilities, ambiguous or underspecified requests, long multi-turn sessions, and unusual operational scenarios that scripted tests don’t anticipate.
• Manually review agent traces and outputs to judge reasoning quality, appropriateness of actions, and safety, and use those findings to improve automated checks.
• Execute manual regression and release verification passes in staging and customer-like environments before new agent capabilities ship.
• Conduct manual red-teaming sessions (prompt injection, jailbreaks, tool misuse, unsafe actions) in partnership with security teams, then convert successful attacks into automated test cases.
• Support user acceptance testing and pilot rollouts with Forward Deployed Engineers, capturing real-world failures and feeding them back into test suites.
• Write clear test plans, test charters, and bug reports, and maintain manual test documentation where automation isn’t yet practical or cost-effective.

Datasets, Metrics, and Quality Strategy

• Create and manage golden datasets and labeled test sets, including edge cases, ambiguous inputs, and adversarial prompts specific to industrial and operational contexts, with tooling for versioning and drift detection.
• Design rubrics and run human-in-the-loop evaluations where automated scoring isn’t reliable enough.
• Define and instrument quality metrics beyond simple accuracy (groundedness, hallucination rate, task success rate, latency/cost tradeoffs, and safety violations) and build dashboards to track them over time.
• Test agent behavior across the full action loop (planning, tool selection, tool execution, error recovery, and final output), not just the final response.
• Investigate and triage failures where the root cause could be the model, the prompt, the tool/API, or the orchestration logic, and turn them into reproducible, actionable bug reports.
• Establish quality bars, release criteria, and sign-off processes for new agent capabilities, blending automated gates with manual verification.
• Decide what to automate and what to keep manual, and continually shift repeatable manual work into automation.
• Mentor engineers on testing strategies and test-driven practices for probabilistic, LLM-driven systems.
• Advocate for testability, observability, and tracing in agent architecture from day one.

• 5+ years as an SDET, QA engineer, or software engineer with a strong testing focus, with demonstrated ownership of test strategy and automation for complex distributed systems.
• Proven experience in both manual and automated testing, including exploratory testing, test planning, and writing high-quality bug reports.
• Strong programming skills (Python preferred) with a software engineering mindset: clean, maintainable, well-reviewed code for frameworks, data pipelines, and tooling.
• Experience building test frameworks and infrastructure from the ground up, not just writing test cases within an existing framework.
• Hands-on experience with CI/CD systems (e.g., GitHub Actions, GitLab CI, Jenkins) and containerized test environments (Docker, Kubernetes).
• Experience testing APIs and microservices, including contract, integration, and end-to-end testing.
• Hands-on experience testing LLM-based products, chatbots, or AI agents, and an understanding of why traditional deterministic assertions break down for generative systems.
• Practical experience with eval frameworks or tooling (e.g., promptfoo, DeepEval, RAGAS, LangSmith) or a track record of building your own.
• Understanding of how LLM agents work: prompting, tool/function calling, context management, RAG, memory, and orchestration frameworks.
• Experience designing test data and labeled datasets, including sourcing, sampling, and managing dataset drift over time.
• Familiarity with LLM-specific failure modes: hallucination, prompt injection, context poisoning, tool misuse, goal drift, and non-determinism.
• Comfort operating in ambiguity, defining what “correct” means for a task when there’s no single right answer.
• Strong written communication skills for turning fuzzy quality signals into clear, actionable findings for engineering and product stakeholders.

Preferred

• Experience with human-in-the-loop evaluation workflows (labeling pipelines, inter-rater reliability, rubric design).
• Experience with performance and load testing tools (e.g., k6, Locust) and chaos or fault-injection testing.
• Background in ML/data science sufficient to read model evals and statistical significance.
• Experience red-teaming or doing adversarial/security testing on ML systems.
• Familiarity with observability and tracing tools for LLM applications (e.g., LangSmith, Arize, Langfuse, Weights & Biases) and general observability stacks (OpenTelemetry, Grafana, Datadog).
• Experience testing systems in industrial, IoT, or operational technology (OT) environments, including industrial protocols (OPC UA, MQTT, Modbus) or simulation and hardware-in-the-loop setups.
• Experience supporting UAT, pilots, or customer-facing validation of complex products.
• Experience setting up test and eval infrastructure from scratch at a startup or fast-moving team.

• An engineer who is equally comfortable writing a test framework and sitting down to break an agent by hand.
• Someone who can build rigorous evaluation systems for problems that don’t have a single right answer, and who knows when human judgment is the right tool.
• A systems thinker who enjoys turning ambiguous agent behavior into measurable, trustworthy signals.
• A strong collaborator who partners well with ML engineers, backend engineers, and Forward Deployed teams.

Why Join Nexxa.AI ?

• Innovative Environment: Play a critical role in transforming heavy industries through groundbreaking AI and automation technologies.
• Collaborative Culture: Be part of a team that values innovation, discipline, and continuous improvement.
• Professional Growth: Benefit from significant opportunities for career development and advancement.
• Competitive Compensation: Enjoy a comprehensive salary and equity package reflective of your expertise and contributions.

If you’re passionate about AI quality and eager to help define what trustworthy autonomous systems look like in heavy industry, we’d love to connect.