Teams at Nexxa.ai

Own quality for AI agent systems by building test frameworks, evaluation harnesses, regression suites, simulators, CI/CD quality gates, and API, integration, performance, and reliability tests. Conduct exploratory, manual, red-team, and release testing; evaluate agent traces, safety, reasoning, and task completion; manage labeled datasets and quality metrics; investigate failures; define release criteria; and mentor engineers on testing probabilistic systems.

Own quality for AI agent systems through automated test frameworks, evaluation harnesses, regression suites, CI/CD quality gates, simulators, and API, integration, performance, and reliability testing. Perform exploratory testing, trace review, manual red-teaming, release verification, and UAT support. Build datasets, metrics, rubrics, dashboards, and release criteria while investigating failures and mentoring engineers on testing probabilistic LLM systems.

Manage technical project execution across Applied AI and Core Engineering teams. Own project decomposition, estimation, timelines, dependencies, risk tracking, and status reporting. Coordinate engineering, DevOps, testing, and client delivery teams; identify blockers and support technical triage across AI agents, infrastructure automation, workflow orchestration, CI/CD, and platform architecture. Drive prioritization, communication, iterative delivery, and execution against shared business goals.