syedhussain shah

Continued as AI quality engineering lead for InterWiz.ai and took over customer success for the platforms client companies. - Built a persona-driven LLM agent (Python, FastAPI, Groq, n8n) that simulates interview candidates with configurable personalities and behaviors, using personas extracted automatically from PDF resumes, for automated end-to-end interview simulations - Grew the QA team from three to five and led four QA engineers - Led onboarding for client companies and aligned their requirements wi

Worked on InterWiz.ai(https://interwiz.ai/), an AI interview platform incubated by Emumba, from its early days. Joined as the first QA hire and built the QA and LLM quality function from scratch. - Set up LLM evaluation and observability in LangSmith: tracing and cost tracking for every LLM call, golden datasets built from recruiter-validated scores, and model benchmarking with custom evaluators and LLM-as-judge scoring - Red-teamed the AI interviewer for prompt injection, prompt leakage, and guardrail a