Senior Data Engineer, LLM

This is a fully remote position, open to applicants in United States.

📋 Description

• Develop production agents and multi-step agent workflows.

• Design and execute MCP servers and tool interfaces that connect agents to the data platform.

• Make architectural decisions regarding agents versus deterministic pipelines, agent decomposition, and human-in-the-loop checkpoints.

• Establish practices for agent evaluation, datasets, LLM-as-judge workflows, regression testing, metrics, tracing, and observability.

• Manage agentic workloads in Airflow 3.x on Astronomer.

• Create long-running or interactive agent workloads utilizing AWS ECS/Fargate and services triggered by events or APIs.

• Model and implement semantic definitions over Snowflake and dbt environments.

• Construct and maintain Snowflake Semantic Views and Cortex Analyst semantic models.

• Capture lineage, freshness, descriptions, classification and sensitivity tags, and usage signals.

• Assess catalog and metadata tools and provide recommendations for build-versus-buy scenarios.

• Design extraction pipelines for various formats including PDFs, presentations, spreadsheets, emails, and web content.

• Build schema-constrained extraction processes with confidence scoring, source citations, and low-confidence handling.

• Implement chunking, embedding, and retrieval strategies for RAG and agentic retrieval.

• Design human review processes and incorporate corrections into evaluation datasets.

• Define and implement scalable data architecture, including tiered/medallion structures, ELT, governance, quality, security, and access controls.

• Create and maintain Python ingestion pipelines across REST APIs, SaaS connectors, file drops, and incremental Snowflake loads.

• Contribute to dbt models, tests, and documentation.

• Implement features such as idempotency, retry semantics, token and budget caps, circuit breakers, structured logging, and audit trails.

• Adhere to Git-based workflows that include code review, CI/CD, and environment promotion.

• Mentor colleagues and act as a technical leader and client-facing resource.

• Present architectural choices, document designs, work independently on ambiguous issues, and communicate project updates.

⛳️ Requirements

• Over 7 years of practical experience in data engineering or software engineering.

• At least 5 years of experience with major cloud platforms.

• Bachelor's degree or higher in Computer Science, Engineering, or a related technical field (or equivalent experience).

• Proven experience deploying LLM-powered or agentic systems to production.

• Strong understanding of tool and function calling, structured outputs, retrieval/RAG, planning loops, multi-agent decomposition, and human-in-the-loop processes.

• Experience with agent evaluation and observability, including eval datasets, LLM-as-judge, regression testing, tracing, and cost/latency monitoring.

• Familiarity with the Anthropic Claude API or similar frontier model APIs.

• Experience with agent frameworks like Claude Agent SDK and/or OpenAI Agents SDK / Assistants API.

• Experience integrating models with enterprise data through MCP and/or similar tool-integration methods.

• Daily working proficiency with Claude and ChatGPT as development tools.

• Expertise in Python, including typing, testing, packaging, and asynchronous programming.

• Advanced SQL skills with strong analytical and dimensional data modeling capabilities.

• Extensive hands-on experience with Apache Airflow.

• Proficient with Snowflake, dbt, AWS, Docker, and infrastructure-as-code practices.

• Experience creating and managing robust CI/CD pipelines.

• Proven experience extracting structured data from documents on a large scale, including at least one layout-heavy domain.

• Familiarity with modern document parsing tools.

• Experience with embeddings, chunking strategies, and vector or hybrid retrieval techniques.

• Self-motivated and autonomous, with strong problem-solving and critical thinking abilities.

• Excellent verbal and written communication skills in professional English.

• Full availability during US Eastern Time business hours (09:00–17:00 ET).

• Background checks may be necessary for specific positions/projects.

🏝️ Benefits

• Fully remote work environment.

• Flexible scheduling options.

• Unlimited Paid Time Off (PTO).

• Paid parental and bereavement leave.

• Opportunities to work with globally recognized clients, enhancing your resume.

• Access to a top-tier team for professional growth and learning.