Description

You will provide L1 through L3 application support for Large Language Model (LLM) based applications while building automated testing frameworks.

Responsibilities

• Provide L1, L2, and L3 support for LLM-based applications, ensuring timely issue resolution and performance monitoring.
• Develop and implement automated testing frameworks to validate the functionality, performance, and reliability of applications and LLMs.
• Create and maintain test scripts for unit, integration, and end-to-end testing, integrating them into CI/CD pipelines.
• Conduct root cause analysis for recurring issues and implement preventive measures to ensure scalability.
• Collaborate with development teams to troubleshoot complex technical issues and maintain detailed documentation.

Required Skills

• Proficiency in Python, SQL, R, and JavaScript.
• Experience with core AWS services including EC2, S3, and RDS.
• Experience developing web applications using frameworks such as Streamlit, Shiny, Vue, or React.
• Knowledge of machine learning frameworks and libraries like TensorFlow, PyTorch, or scikit-learn.
• Understanding of container strategies including Docker and ECS.
• Deep knowledge of databases such as Postgres, Elasticsearch, and Redshift, including SQL vs NoSQL and optimization.
• Experience with automated testing tools such as pytest, Selenium, or JUnit.
• Familiarity with Agile SDLC, distributed source code control, and CI/CD processes.

Preferred Skills

• Experience in BioPharma environments.
• Proven experience working with predictive modeling or Large Language Models.

Key Skills

Education

Bachelor's degree