Responsibilities:

• Work with data warehouse team, to maintain real time data pipeline of CS business domain, to ensure timely and high-quality data inputs to the AI models.

• Design, implement, and refine LLM prompts for enhanced attribution analysis of CS conversations.

• Work closely with Ops teams to increase the stability of LLM solutions in a cloud or on-prem environment.

• Conduct A/B testing and iterative improvements on LLM performance, and maintaining result accuracy.

• Develop and maintain back-end services and automation scripts using Java or Python, ensuring seamless integration with existing systems.

• Troubleshoot performance bottlenecks, optimize code, and safeguard data security and privacy.

• Collaborate with CS, BI, and SL teams to gather requirements, clarify feature demands, and communicate technical constraints.

• Maintain clear, concise documentation of data work flows, LLM prompt templates, and best practices.
  
  

Qualifications:

• Bachelor’s or Master’s degree in Computer Science, Data Science, or a related field.

• 5+ years of hands-on experience in Java data processing and pipeline development.

• Experience with SQL/NoSQL databases, ETL pipelines, and data workflow orchestration tools (e.g., Airflow).

• Proficient in Java / Python (at least one language) and Hive & Spark SQL programming languages.

• Hands-on experience with AWS, GCP, or Azure is a plus.

• Experience with LLM or NLP projects is highly desired

• Excellent communication and teamwork skills, with the ability to work in a cross-functional environment.

• Fluency in English is required to be able to coordinate with overseas partners and stakeholders. Additional languages would be an advantage.