QA Engineer (AI Systems)

Nexxa.AI•Sunnyvale, CA

About The Position

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. 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.

Requirements

5+ years in QA/SDET roles, with demonstrated ownership of test strategy for complex systems.
Hands-on experience testing LLM-based products, chatbots, or AI agents — you understand why traditional deterministic test 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.
Strong scripting/programming ability (Python preferred) to build test automation, data pipelines, and eval tooling.
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.
Comfortable 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.

Nice To Haves

Experience with human-in-the-loop evaluation workflows (labeling pipelines, inter-rater reliability, rubric design).
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/tracing tools for LLM applications (e.g., LangSmith, Arize, Langfuse, Weights & Biases).
Experience testing AI systems in industrial, IoT, or operational technology (OT) environments.
Prior experience setting up eval infrastructure from scratch at a startup or fast-moving team.

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.