Job Description
Personal Qualities You Will Need
- Excellent documentation and communication skills
- Ability to thrive in a rapidly evolving environment, both independently and within small cross-functional teams
- Self-starter, attention to detail and results orientated, able to work under minimal guidance
- Personal initiative for continual improvement
- Desire and ability to gain business domain knowledge
Required Skills/Technology
- 2+ years of data engineering experience, preferably in support of analytics/ML/LLM applications
- 1+ years deploying/supporting LLM agents
- Python
- Must have experience using ChatGPT, Claude, or LLama models
- Designing and maintaining vector database preferably using Pinecone or similar tools
- Creating/maintaining database structures for machine learning and LLM models.
- LLM prompt engineering and prompt tuning
- LLM toolkits like Langchain or AutoGen, structured outputs, functions, tool calling, and Agents
- Parquet, JSON file manipulation and querying
- Maintaining chat history using external databases, preferably using dynamoDB
- Designing data models and develop database structures in Microsoft SQL Server
- Data Warehouse experience, including designing data models and creating database structures in Microsoft SQL Server
- Developing ETL solutions, building complex SQL queries, writing stored procedures, functions, views, and triggers
- Creating automated data migration tasks like data importing and exporting
- Outstanding analytical, quantitative, problem-solving, and critical thinking skills
- Data quality best practices, data validation, and troubleshooting
- Experience using source control tools, such as Azure DevOps and GitHub
- Strong written and verbal communication skills, including the ability to present detailed analyses to a broad audience range
Experience With These Is a Major Plus
- LangGraph and similar tools for designing LLM Graphs
- Business Intelligence applications, preferably Tableau
- Creating test cases for periodic monitoring of LLM models
- Postgres SQL
- MongoDB
- Shell, Bash and other command line languages
- Tuning training data and metadata for LLMs, using either open source huggingface models or chatgpt/anthropic toolkits
- CI/CD pipelines using Github Actions or similar tools
- Glue, Athena, EMR, EKS, DynamoDB
- Lambda jobs
- Agile and Scrum methodologies
Company Description
Easalytics has been providing cutting-edge analytics and data science solutions to the fitness industry for over 5 years. Our team is 100% remote and values communication, teamwork, positivity, innovation, personal initiative, and a desire to improve everything.
Easalytics has been providing cutting-edge analytics and data science solutions to the fitness industry for over 5 years. Our team is 100% remote and values communication, teamwork, positivity, innovation, personal initiative, and a desire to improve everything.