AI Engineer

Overview In this role, you will design and build production-grade agent and RAG systems powering intelligent automation across NetBrain’s platform. You’ll own architecture, evaluation, and production reliability for scalable AI components that support diagnostic troubleshooting and change management. You’ll work closely with cross-functional teams to deliver high-quality, safe, and impactful automation. A key hook is shaping AI-powered capabilities at scale for managing hybrid multi-cloud networks. Compensation / Benefitsbase salary plus bonus401kmedical/dental coverageTotal Rewards philosophy ResponsibilitiesDesign core agent platform capabilities, including orchestration patterns and tool execution layersDevelop reusable agent skills and a standardized tool ecosystemImplement enterprise-grade controls with human-in-the-loop workflows and policy enforcementDesign and implement RAG services with hybrid retrieval, embeddings, and citation behaviorDefine evaluation frameworks and quality metrics for reliable outputsBuild automated evaluation and regression pipelines for production scaleEstablish observability (tracing, metrics, alerting) and optimize latency, throughput, and costPrototype and productionize emerging AI approaches (GraphRAG, knowledge graphs, MCP integrations)Evaluate AI frameworks and guide platform decisions (LangChain, LangGraph, AutoGen, LlamaIndex)Diagnose and resolve complex AI system issues and drive system design through prototyping and benchmarkingLead technical decisions and ensure production readiness Key requirementsBS in Computer Science, AI, Electrical Engineering, or related field5+ years of software engineering, including production-grade LLM, agent, or RAG systemsProven track record shipping AI-powered features in productionStrong Python skills (API design, testing, error handling)Working proficiency in C# or C++Deep understanding of RAG system design and evaluation methodologiesExperience building evaluation frameworks (test sets, metrics, regression pipelines)Understanding of LLM security risks (prompt injection, data leakage)Experience with graph databases, knowledge graphs, or GraphRAG preferredExperience designing human-in-the-loop systems and execution controls preferredExperience with agent frameworks (LangChain, LangGraph, AutoGen, LlamaIndex)Willingness to commute to Burlington, MA twice a weekthrives in ambiguityquality- and safety-focusedstrong problem-solving mindsetPythonC# or C++RAG system design