Agentic Data Engineer II

EchoStar is tackling the realities of scaling data infrastructure for modern analytics and emerging AI initiatives. In this onsite role in Littleton, CO, you will design and deliver production-grade data pipelines and workflows that support machine learning and large language model (LLM) consumption, with a focus on reliability, observability, governance, and cost-effective operations.

As an Agentic Data Engineer II, you will build pipelines for LLM feature stores and AI application workflows, including automated monitoring and self-healing mechanisms. Your work will also help structure complex datasets into semantic layers for low-latency access by downstream AI systems and analytical queries.

Responsibilities

• Implement scalable data pipeline designs that optimize current infrastructure performance and improve resource utilization
• Use cost-effective engineering practices to prioritize work that improves operational efficiency and data deliverability
• Build and maintain reliable pipelines for LLM feature stores and AI application workflows
• Develop automated monitoring and self-healing mechanisms to detect workflow failures and trigger corrective actions
• Integrate observability tools to track data freshness, lineage, and baseline performance metrics across production environments
• Structure complex datasets into standard semantic layers to enable low-latency access for downstream AI systems and analytical queries
• Participate in at least one in-person interview

Requirements

• Practical experience developing and deploying production-grade data pipelines within cloud environments
• Ability to evaluate technical stacks and optimize existing data processing workflows before introducing new tools
• Ability to build new AI Agents to support business operations
• Applied AI skills, specifically integrating large language models and vector datasets into enterprise data pipelines
• Strong proficiency in Python and SQL for data transformation, scripting, and API integration
• Solid skills in Git version control, containerization tools, and CI/CD deployment pipelines
• Proven troubleshooting abilities for diagnosing system bottlenecks and resolving issues within distributed data platforms
• 2 years of experience in data engineering
• Master’s degree in Computer Science, Data Engineering, Artificial Intelligence, or a closely related technical field
• Bachelor’s degree in Computer Science or a related technical field
• At least 1 year of experience with Databricks, including Spark optimization and Delta Lake architecture
• At least 1 year of experience with Snowflake, including building and optimizing relational data models
• At least 1 year of experience with Python and SQL for data manipulation
• Visa sponsorship not available for this position

Technologies

• Python, SQL
• Git, CI/CD
• Databricks, Spark, Delta Lake (including Delta Lake architecture)
• Snowflake
• LLM, vector datasets
• Containerization tools

Benefits

• Flexible spending accounts
• HSA
• A 401(k) Plan with company match
• ESPP
• Career opportunities
• Flexible time away plan
• The base pay range shown is a guideline. Individual total compensation will vary based on qualifications, skill level, and competencies. Compensation is based on the role’s location and is subject to change based on work location.

Salary Range: USD $83,160 - $118,800 per year

Location: Littleton, CO (onsite)