Software Development Engineer in Test - AI

SET.Python, Python, Machine Learning, LangChain, Generative AI, AI in Test Automation

Hyderabad, Bangalore, Pune, Chennai, Gurgaon

We are seeking a highly skilled and experienced Lead Python SDET to join our remote team for an exciting project focused on developing AI-based testing solutions.

In this role, you will lead a team of software, system, and test engineers in designing and implementing Langchain components and Langsmith, Vector Databases, building and testing Retrieval Augmentation Generation (RAG) based applications using open source tools and frameworks.

Responsibilities

Lead a team of software, system, and test engineers in designing and implementing Langchain components and Langsmith, Vector Databases, building and testing Retrieval Augmentation Generation (RAG) based applications using open source tools and frameworks
Collaborate with cross-functional teams to ensure the accuracy and completeness of testing solutions
Develop and maintain documentation, including technical specifications, data flow diagrams, and data mappings
Evaluate and test LLMs using tools and open-source libraries
Ensure adherence to coding standards and best practices in software development

Requirements

Minimum of 8 years of experience in software, system, and test engineering
Proven track record of leading and mentoring a team of engineers
Bachelor's or Master's degree in Computer Science, Software Engineering, or related fields
Strong Python development skills with proficiency in libraries for Machine Learning/Deep learning like scikit-learn, Pandas, Numpy, and Matplotlib
Experience in designing and implementing Langchain components and Langsmith, Vector Databases, building and testing Retrieval Augmentation Generation (RAG) based applications using open source tools and frameworks
Mandatory working project experience in testing of AI and not just implementing AI in testing
Good verbal and written communication skills in English at a B2 level

Nice to have

AI Developer certification from any of the cloud providers (AWS, Azure, GCP)
Exposure to tools and open-source libraries for the evaluation and testing of LLMs