Machine Learning Scientist/Engineer - Text to SQL

ALTEA Healthcare is a leading healthcare organization committed to revolutionizing the delivery of outpatient/post-acute care. We are seeking an experienced Machine Learning Scientist/Engineer with deep subject matter expertise in working with LLMs and SQL to join our team. As an important member of the AI team, this person will contribute significantly to designing, implementing, and deploying GenAI applications, to improve care delivery and quality for post-acute patients. This person will lead the design and development work to build a system that can convert natural language queries to handle the use cases like building SQL query statements for searching tables in DB or searching for cohorts with specific medical criteria. The ideal candidate possesses a deep understanding of LLM techniques, database management systems, SQL Query optimization, and a passion for building intelligent systems in healthcare.

Responsibilities:

• Develop a system that converts natural language queries into a structured format for searching SQL tables or documents
• Use/fine-tune language models to interpret and convert natural language queries into SQL statements
• Develop a mechanism to summarize SQL tables into user-level summary text, providing concise and meaningful insights from retrieved data
• Help build a scalable system capable of efficiently handling a large volume of queries, ensuring high performance and minimal latency
• Optimize SQL queries to ensure efficient data retrieval
• Develop system evaluation processes that ensure accuracy, fairness, reproducibility, and scalability
• Document system architecture, design decisions, and codebase to facilitate future maintenance and enhancements

Requirements:

• Bachelor’s/Master’s degree in Computer Science, Data Science, Machine Learning, or a related field
• At least 2 years of experience with Pytorch/TensorFlow, NLP libraries (such as NLTK, spaCy), Hugging Face Transformers, Langchain, VectorDB
• At least 3 years of experience writing SQL queries, including complex joining queries
• Demonstrated experience with Text-to-SQL projects
• Experience with building ML pipelines using prompt engineering/optimization and RAG
• Good understanding of SQL and experience working with relational database management systems (Microsoft SQL Server)
• Experience with query optimization techniques
• Ability to work independently and collaboratively, manage priorities, and deliver high-quality results within project timelines
• Familiarity with cloud-based data warehousing platforms
• Preferred experience working with Electronic Health Records (EHR)

Job Type: Full-time

Pay: Competitive pay and benefits and extremely valuable startup stock options

Schedule: Full Time

• Work Location: Hybrid position in Houston preferred, with remote options available for exceptionally qualified candidates.

Benefits:

• 401(k)
• Dental insurance
• Health insurance
• Vision insurance