AI Data Engineer for LLM Agents

TieTalent; Connecticut; Remote; USD 70,000 - 90,000; Full time

Job summary

A growing B2B SaaS company in Connecticut seeks a Data Engineer to join their remote team. The role focuses on data engineering for analytics and machine learning. Candidates should be self-starters with strong communication skills and a passion for data. The company values innovation and teamwork, providing cutting-edge solutions in the fitness industry.

Qualifications

• 2+ years of data engineering experience supporting analytics/ML applications.
• Experience with LLM agents and deploying LLM models.

Responsibilities

• Design and maintain vector databases and database structures for ML.
• Automate data migration tasks and ensure data quality.

Skills

Documentation

Communication

Problem Solving

Attention to Detail

Self-Starter

Tools

Python

Azure DevOps

GitHub

Microsoft SQL Server

Postgres SQL

MongoDB

AWS

Job description

Get AI-powered advice on this job and more exclusive features.

About the Job

Overview Of The Company

Easalytics, a subsidiary of CTComp, is a growing B2B SaaS company providing advanced analytics and data science capabilities to the fitness industry. Our expertise includes software development, data integration, data warehousing, machine learning, AI, data visualization, and statistical analysis. We are looking for a software development professional with a focus on data engineering who is passionate about data and analytics. Join our small, innovative team to disrupt the industry!

Personal Qualities You Will Need

• Excellent documentation and communication skills
• Ability to thrive in a rapidly evolving environment, independently and in small teams
• Self-starter with attention to detail and results-oriented
• Personal initiative for continual improvement
• Desire and ability to gain business domain knowledge

Required Skills/Technology

• 2+ years of data engineering experience supporting analytics/ML/LLM applications
• 1+ years deploying/supporting LLM agents
• Proficiency in Python
• Experience with ChatGPT, Claude, or LLama models
• Designing and maintaining vector databases (preferably Pinecone)
• Creating and maintaining database structures for ML and LLM models
• LLM prompt engineering and tuning
• Experience with LLM toolkits like Langchain or AutoGen
• Handling Parquet, JSON files, and querying
• Maintaining chat history using external databases (preferably DynamoDB)
• Designing data models and database structures in Microsoft SQL Server
• Data warehouse experience, including ETL development and SQL querying
• Automating data migration tasks
• Strong analytical, problem-solving, and critical thinking skills
• Data quality practices, validation, and troubleshooting
• Experience with source control tools like Azure DevOps and GitHub
• Excellent written and verbal communication skills

Preferred Skills

• LangGraph and similar tools for LLM graph design
• Business Intelligence tools (e.g., Tableau)
• Postgres SQL, MongoDB
• Shell, Bash scripting
• Training data and metadata tuning for LLMs
• CI/CD pipelines (GitHub Actions)
• AWS services (Glue, Athena, EMR, EKS, DynamoDB, Lambda)
• Agile and Scrum methodologies

Company Description

Easalytics has been delivering cutting-edge analytics and data science solutions to the fitness industry for over 5 years. Our fully remote team values communication, teamwork, positivity, innovation, personal initiative, and continuous improvement.

Additional Information

• Location: Connecticut, United States
• Work experience: Data Engineer, Fullstack, Machine Learning, NLP
• Languages: English
• Seniority level: Entry level
• Employment type: Full-time
• Job function: Information Technology
• Industries: Technology, Information, and Internet