QA Engineer

Nexxa is building the best AI systems for heavy industries — enabling machines, systems and operations to think, decide and act autonomously across manufacturing, large-scale infrastructure, logistics and legacy environments.

Our mission is to translate deep technical breakthroughs into operational reality, solving some of the hardest systems-level problems in industry.

Role Overview

We're looking for a Lead / Senior / Staff QA Engineer to own quality for Nexxa's AI agent systems — products that plan, call tools, and take multi-step actions autonomously in industrial environments. This isn't traditional UI testing: you'll be designing evaluation frameworks for non-deterministic, tool-using systems, building golden datasets, catching regressions in reasoning quality, and stress-testing agent behavior under adversarial and real-world edge-case conditions.

You'll work closely with ML engineers, backend engineers, and Forward Deployed Engineers to define what "good" looks like for an agent operating in high-stakes industrial settings, then build the infrastructure and processes to measure it continuously.

Key Responsibilities

• Design and build evaluation harnesses and regression suites for LLM-based agents, covering reasoning quality, tool-call correctness, task completion, and multi-turn coherence.

• Develop golden datasets and labeled test sets, including edge cases, ambiguous inputs, and adversarial prompts specific to industrial and operational contexts.

• Define and track quality metrics beyond simple accuracy — groundedness, hallucination rate, task success rate, latency/cost tradeoffs, and safety violations.

• Build automated pipelines that run evals on every model, prompt, or tool-integration change, and integrate them into CI/CD.

• Conduct structured red-teaming and adversarial testing (prompt injection, jailbreaks, tool misuse, unsafe actions) in partnership with security teams.

• 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.

• Partner with ML and backend engineers to translate eval failures into actionable, reproducible bug reports.

• Establish quality bars and sign-off criteria for new agent capabilities before they reach customer environments.

• Mentor other engineers on testing strategies specific to probabilistic, LLM-driven systems.

• Advocate for testability and observability in agent architecture from day one.