Senior Software Engineer, Data

This is a fully remote position, open to applicants in New York.

📋 Description

• Design and oversee ETL pipelines that analyze and categorize unstructured data for Retrieval-Augmented Generation (RAG) systems.

• Assist in the creation of agent-based architectures utilizing reasoning and action patterns.

• Develop and maintain agent workflows leveraging node-based orchestration frameworks.

• Create and implement systems for agent memory.

• Design prompts for system interactions and intent-handling to enhance reliable agent communications.

• Generate evaluation tests, datasets, and performance metrics to assess and enhance LLM agent performance.

• Develop tools enabling LLM agents to interact with external systems and services.

• Implement best practices concerning guardrails, prompt security, and user-generated content.

• Collaborate closely with team engineers.

⛳️ Requirements

• Proven experience in developing RAG pipelines or ETL workflows for unstructured documents.

• Background in working with LLM-based systems or AI-driven applications.

• Knowledge of agent architectures, including ReAct.

• Hands-on experience with workflow orchestration frameworks like LangGraph or other node-based systems.

• Experience in implementing agent memory systems (e.g., AgentCore Memory API or equivalent), encompassing both short-term and long-term memory strategies.

• Proficiency in crafting system prompts and designing prompt interactions for LLM applications.

• Experience in evaluating and conducting performance testing for LLM agents.

• Ability to create evaluation datasets and test scenarios for agent-driven systems.

• Familiarity with guardrails and safety protocols for LLM and agent systems.

• Knowledge of AWS environments and tools, including AWS CLI and STS.

• Strong comprehension of data pipelines and document processing within AI systems.

🏝️ Benefits

• Equality in compensation

• Market-based pay

• Regular compensation reviews

• Automatic pay adjustments at least once a year

• Fair treatment in compensation regardless of race, gender, disability, or age.