Job description
- Design and optimize prompts for large language models (LLMs) to support tasks such as data extraction, summarization, and classification.
- Develop and maintain robust ETL and data pipelines to process structured and unstructured data efficiently.
- Build scalable LLM pipelines with automation and seamless API integration.
- Evaluate and refine LLM outputs to ensure high quality, performance, and cost-effectiveness.
- Research, test, and implement innovative techniques in LLMs and data engineering to improve scalability and performance.
- Monitor and enhance pipelines continuously, addressing bottlenecks and integrating process improvements.
- Collaborate closely with product managers, developers, and data scientists to align AI-driven solutions with business objectives.
- Maintain comprehensive documentation for prompt strategies, data workflows, and pipeline designs.
Qualifications
- Bachelor's degree in Computer Science, Engineering, or a related field.
- Minimum 5 years of experience in AI/ML, Data Science, or related technical roles.
- Strong expertise in machine learning models, natural language processing (NLP), and LLMs.
- Proficiency in Python; knowledge of C#/.NET is a plus.
- Hands-on experience with data pipelines, ETL processes, and modern data engineering tools.
- Experience deploying solutions on cloud platforms (Azure preferred).
- Familiarity with Microsoft Fabric, including Dataflow Gen2, OneLake, Lakehouse, and PySpark.
- Skilled in prompt engineering with a focus on optimizing latency and cost.
- Excellent analytical, problem-solving, and communication skills.
- Ability to work independently and collaborate effectively within cross-functional teams.
Ref. Code: CTR01
ไอเอสเอ็ม เทคโนโลยี
