At Troopr, we’re building world-class AI solutions — from conversational AI to LLM-powered automation — that help top brands like Starbucks, Netflix, Snowflake, and Spotify automate support and elevate user experience. We’re looking for a QA Engineer who’s passionate about delivering flawless web-based B2B SaaS products.

We’re looking for a versatile Prompt Engineer with a strong QA mindset to help shape and refine the intelligence of our AI agents and ensure exceptional product quality. This hybrid role blends prompt engineering, GenAI testing, and quality assurance for high-performance, LLM-powered customer and employee support automation.

You’ll work at the intersection of product design, engineering, and AI, ensuring the accuracy, usability, and robustness of chatbot workflows and GenAI integrations in a fast-paced B2B SaaS environment.

What You’ll Do

• Prompt Engineering & LLM Optimization Design, experiment, and iterate on prompts to optimize LLM responses for support automation
• Build reusable prompt libraries and scalable test frameworks
• Integrate prompt flows into AI agent pipelines with product and engineering teams
• Evaluate prompt strategies using techniques like RAG, few-shot learning, and role conditioning GenAI/LLM QA & Evaluation Execute functional, regression, and exploratory testing of GenAI-driven features
• Analyze LLM outputs for coherence, hallucinations, factual accuracy, and ethical risks
• Identify edge cases and UX inconsistencies in real-world chatbot interactions System QA & Performance Testing
• Lead performance/stress testing of AI-driven backend and frontend systems
• Collaborate cross-functionally in Agile teams to maintain a high-quality user experience
• Document bugs, usability gaps, and provide insights to improve product excellence

What We’re Looking For

• 2+ years of experience testing GenAI/chatbot applications or LLM-based products
• Hands-on knowledge of tools like OpenAI, Anthropic, LangChain, or similar Experience with B2B SaaS platforms, particularly in AI support automation
• Familiarity with QA tools like Jira, TestRail, and evaluation of LLM outputs
• Strong problem-solving skills and attention to edge cases
• Comfortable working in fast-paced, startup environments with high ownership
• Excellent verbal and written communication skills
• Experience with AI observability tools and A/B testing for prompt strategies Exposure to few-shot, chain-of-thought prompting, or guardrails Familiarity with performance testing tools (e.g., JMeter, Locust) Background in NLP, linguistics, or cognitive science Why Join Us? At

Enjo.ai, you’ll help build cutting-edge AI support agents that serve real business users — not just lab demos. You’ll contribute to shaping both the intelligence and quality of our product. If you're excited by GenAI, care deeply about LLM behavior, and want to ensure it performs reliably and ethically in production — let’s talk.