Job Description | Mid-Senior Data Scientist
Job Title: - Mid-Senior Data Scientist - Snowflake Cortex Specialist
Location: Remote
Start Date: Immediate availability preferred
The Opportunity:
We are seeking a highly skilled Mid-Senior Data Scientist with deep expertise in Snowflake's native data science functionalities . This role will be crucial in the initial phase of developing and implementing an enterprise-wide Large Language Model (LLM) powered chat interface, leveraging customers' structured data products within Snowflake. The ideal candidate will possess a strong hands-on background in data science, a comprehensive understanding of Snowflake's ecosystem, and a passion for leveraging cutting-edge AI technologies. This is a remote contract position.
Responsibilities:
Lead the solution design of an enterprise-grade LLM-based chat interface leveraging Snowflake's native data science features to interact with customers' structured data products.
Define, implement, and manage the Semantic Model Specs within Snowflake to ensure accurate and contextually rich responses from the LLM.
Expertly configure and optimize Snowflake Cortex Analyst to extract relevant information and insights from customers' structured data products for the LLM.
Design and implement the integration strategy for the LLM-powered chat interface, which will involve either developing a user interface directly within Snowflake using Streamlit to interact with the configured Snowflake Cortex solution or establishing a robust API integration between the Snowflake Cortex solution and an existing enterprise chat bot service.
Collaborate with relevant teams to understand data structures and access requirements for customer data products within Snowflake.
Evaluate and recommend appropriate LLM models and prompt engineering techniques within the Snowflake environment for interacting with structured data.
Implement initial testing and validation procedures for the chat interface, considering integration with Streamlit or existing enterprise bot services via API.
Document all aspects of the development process, including solution design, data flows, and configurations relevant to the contract deliverables.
Provide knowledge transfer and documentation to the internal team for ongoing development and integration efforts.
Must have a strong understanding of Snowflake Role-Based Access Control (RBAC) and best practices for governing access controls within Snowflake.
Qualifications:
Bachelor's or Master's degree in Computer Science, Data Science, Statistics, or a related quantitative field.
5+ years of hands-on experience as a Data Scientist, with a significant focus on working within the Snowflake environment.
Deep and demonstrable expertise in leveraging Snowflake's native data science features, including but not limited to:
Snowpark (Python, Scala, Java) for data interaction and potential model deployment.
Snowflake ML functions and libraries.
Data governance and security features within Snowflake.
Proven ability to configure and effectively utilize Snowflake Cortex Analyst for information retrieval and analysis from structured data.
Strong understanding and practical experience in defining and managing Semantic Model Specs within Snowflake.
Solid understanding of Large Language Models (LLMs), their capabilities, and limitations in the context of structured data.
Experience with prompt engineering techniques for LLMs.
Proficiency in SQL and data manipulation within Snowflake.
Strong analytical and problem-solving skills with the ability to translate requirements into technical solutions for a chat interface.
Excellent communication and collaboration skills in a remote working environment.
Must have a strong understanding of Snowflake Role-Based Access Control (RBAC) and best practices for governing access controls within Snowflake.