The Senior AI Test Engineer will be responsible for designing and executing comprehensive test strategies for AI-driven systems. They will ensure the reliability, accuracy, and performance of AI models through rigorous testing protocols.
The candidate will design and maintain automated test suites using Playwright while integrating AI tools to optimize test planning, execution, and defect analysis. They will collaborate with cross-functional teams to practice shift-left quality engineering and ensure high product reliability.
Design, develop, and maintain full-stack web applications while managing the entire lifecycle from database schema to frontend UX. Collaborate directly with client stakeholders to translate requirements into technical solutions and provide ongoing post-launch support.
The role involves leading quality reviews, creating comprehensive test strategies, and managing the defect lifecycle for a SaaS platform. You will collaborate with cross-functional teams to define QA standards, perform automation and manual testing, and contribute to continuous process improvement.
Design and build autonomous AI agents capable of tool use, memory, and complex multi-step task execution. Develop scalable backend services and observability frameworks to ensure reliability, performance, and quality of AI systems.
Design, implement, and maintain web scrapers to collect alternative datasets while performing data cleaning and transformation. Collaborate with cross-functional teams to build efficient data processing workflows and maintain alerting systems for data integrity.
Design, implement, and maintain web scrapers to create proprietary datasets for an asset management firm. Perform data cleaning and manipulation using Pandas and manage data ingestion and scheduling via Airflow.
Design and implement a Python-based tool using LLMs and machine learning to automate quality control checks for vendor data sets. Collaborate with Data Managers and Software Engineers to improve data quality coverage and develop compliance dashboards.