Data Engineer

Bold Penguin is a digital broker for commercial insurance that uses digital distribution, wholesale capabilities, and AI-driven insights to transform insurance risk placement. The Data Engineer will build scalable data pipelines, APIs, microservices, vector search systems, and AI-driven data services while collaborating with engineering, analytics, and AI teams. The role also involves improving production reliability, evaluating AI models, and resolving issues to exceed SLAs.

Responsibilities:

• Collaborate with Senior Data Engineers, Data Analysts, and AI specialists to connect, extract, and transform data from diverse structured and unstructured sources
• Design and optimize large-scale data processing pipelines to support both traditional analytics and AI-driven workloads
• Build APIs and microservices that power intelligent systems leveraging LLMs, embeddings, and AI agents
• Implement and maintain vector databases and semantic search pipelines for retrieval-augmented generation (RAG) and contextual chat experiences
• Contribute to prompt engineering, model evaluation, and orchestration workflows that enable autonomous AI agents to interact with data and tools
• Integrate AI frameworks and orchestration tools (e.g., LangChain, LlamaIndex, CrewAI, or similar) into production data services
• Continuously improve reliability and scalability by identifying enhancements to processing, parallelization, and search pipelines
• Troubleshoot and resolve production issues to exceed SLAs

Requirements:

• Bachelor's degree in Computer Science, Computer Engineering, Data Science, or a related field
• 2+ years of experience in software or data engineering roles
• Strong proficiency in Python and one other language (Java, Node.js, or Go); with experience developing APIs in a microservices architecture
• Strong understanding of data modeling and database technologies, including PostgreSQL and MongoDB
• Experience building or integrating with AI/LLM-powered applications, including prompt templates, embeddings, and RAG pipelines
• Hands-on experience with AI agent frameworks (e.g., LangChain, CrewAI, OpenDevin, or AutoGen) and vector databases (e.g., Pinecone, FAISS, Weaviate, or Chroma)
• Working knowledge of CI/CD pipelines and cloud infrastructure (AWS or CNCF toolkits)
• Excellent written and verbal communication skills, with the ability to document and present complex systems clearly
• Experience with data orchestration frameworks like Apache Airflow or Prefect
• Familiarity with insurance or financial data ecosystems