SR Software Engineer (Data) - Remote, US
Role details
Job location
Tech stack
Job description
We are looking for a Senior Software Engineer with a strong focus on Data and experience building infrastructure for LLM-powered applications and agent-based systems. In this role, you will work on RAG pipelines, agent workflows, and memory systems that allow AI agents to reason, retrieve information, and interact with complex tasks.
You will collaborate with engineers building intelligent agents and help design the data pipelines, evaluation frameworks, and orchestration workflows that support reliable and scalable AI systems.
Note: This opening is only available for candidates based in the United States of America. Applications from other locations will not be considered for the role.
What You'll Do:
- Design and maintain ETL pipelines that process and classify unstructured data for Retrieval-Augmented Generation (RAG) systems.
- Support the development of agent-based architectures using reasoning and acting patterns such as ReAct.
- Build and maintain agent workflows using node-based orchestration frameworks such as LangGraph, including hierarchical and state-machine-based execution.
- Design and implement agent memory systems, including short-term event memory and long-term memory strategies such as summarization, semantic memory, episodic memory, and user preference storage.
- Develop system prompts and intent-handling prompts that support reliable agent interactions.
- Create evaluation tests, datasets, and performance benchmarks to measure and improve LLM agent behavior, including ReAct-based agents.
- Build tools that allow LLM agents to interact with external systems and services.
- Apply best practices around guardrails, prompt security, input sanitization, and safe handling of user-generated content.
- Collaborate closely with engineers across the team and provide guidance to less experienced developers when needed.
Requirements
- Experience building RAG pipelines or ETL workflows for unstructured documents.
- Experience working with LLM-based systems or AI-powered applications.
- Familiarity with agent architectures such as ReAct.
- Hands-on experience with workflow orchestration frameworks such as LangGraph or similar node-based systems.
- Experience implementing agent memory systems (e.g., AgentCore Memory API or similar), including both short-term and long-term memory strategies.
- Experience writing system prompts and designing prompt interactions for LLM applications, including intent handling.
- Experience evaluating and performance testing LLM agents, particularly within ReAct-style workflows.
- Ability to generate evaluation datasets and test scenarios for agent-based systems.
- Understanding of mapping user utterances to intents using RAG and/or LLM-based approaches.
- Understanding of guardrails and safety mechanisms for LLM and agent systems.
- Understanding of agent-specific threat vectors, including prompt injection, tool misuse, and unsafe memory access.
- Familiarity with AWS environments and tools such as AWS CLI and STS.
- Strong understanding of data pipelines and document processing for AI systems.
Nice to have:
- Experience with LangGraph or other agent orchestration frameworks.
- Experience building tools for tool-enabled LLM agents.
- Experience working with hierarchical state machines or complex workflow orchestration patterns.
- Experience designing evaluation frameworks or LLM benchmarking systems.
- Experience working with AI agent security concepts or threat modeling.
Benefits & conditions
4.14.1 out of 5 stars Rochester, NY Remote $96,000 - $129,000 a year - Full-time