AI Engineer II

Responsibilities

• Contribute to building agentic AI workflows, including tool-calling, agent loops, and LLM-driven automation
• Assist in developing and maintaining RAG pipelines involving document ingestion, chunking, embedding, and retrieval
• Implement and iterate on prompt engineering techniques such as few-shot prompting and chain-of-thought
• Work with LangChain and LangGraph for LLM orchestration and task chaining
• Support LLM evaluation by writing datasets and measuring output quality
• Deploy and test LLM-powered features using AWS Bedrock, Lambda, and SageMaker
• Perform data acquisition, cleaning, and transformation for AI/ML pipelines
• Build and evaluate supervised and unsupervised ML models for security use cases

Requirements

• 2–5 years of experience in AI/ML engineering or software engineering with an AI focus
• Foundational hands-on experience with LangChain or similar LLM orchestration frameworks
• Familiarity with prompt engineering concepts and techniques
• Basic understanding of RAG pipelines and retrieval mechanisms
• Awareness of agentic AI patterns such as tool-calling and ReAct
• Working knowledge of AWS Bedrock and/or SageMaker for AI/ML workloads
• Strong Python skills
• Proficiency with pandas, NumPy, and scikit-learn

Preferred Qualifications

• Exposure to cybersecurity, malware datasets, or threat detection domains
• Hands-on experience with vector databases like FAISS, Pinecone, or OpenSearch
• Familiarity with LLM observability tools such as Langfuse or Promptfoo
• Working knowledge of ML/LLM CI/CD pipelines
• Exposure to deep learning frameworks like PyTorch or TensorFlow

About the Company

Rapid7 is a cybersecurity leader dedicated to creating a secure digital world. Our AI Center of Excellence brings together engineers and data scientists to research and deliver production-grade AI systems that protect our customers' attack surfaces through cutting-edge Generative AI and agentic frameworks.