$150K - 220K a year
Lead architecture and design decisions for generative AI integration across multiple engineering teams, mentor engineers, and drive continuous improvement in software architecture.
7+ years engineering/architecture experience, 5+ years leadership, expertise in generative AI platforms, strong Java or C# and Python skills, experience with ML frameworks and MLOps, and cloud-native architecture knowledge.
Job Description: • The Principal Software Architect - GenAI acts as an architecture leader in a domain area in multiple activities and teams. • Responsible for the high-level design/architecture decisions and drives continuous improvement in architecture and engineering across set of software products/services. • Additionally responsible for solutioning and planning for the incorporation of generative AI capabilities across the entire Duck Creek Suite. • Acts as a Domain Architect for the GenAI domain, leading and representing the design/architecture decisions of that domain area. • Provides architectural and technical leadership, participating and leading with Engineering Communities of Practice. • Refines technical backlog items and creation of the overall solution concept and architectural direction for multiple engineering teams. • Provides guidance and support to the developers in multiple engineering teams across our product suite in the completion of stories against design/architecture plans. • Mentor and help develop engineers and architects in their career growth. • Drives and coordinates our technical position with key technology vendors. • Can be hands-on, designing and coding solutions for Agile stories with key architectural impact. Requirements: • Bachelor’s or Masters Degree and/or equivalent experience relevant to functional area • 7+ years of engineering and/or architecture experience • 5+ years supervisory and strategic leadership experience • Generative AI Expertise • Experienced in creating solutions incorporating Generative AI platforms and tooling into production products. • Hands-on experience with LLM integration, RAG pipelines, vector databases, prompt engineering, and hallucination mitigation strategies. • Familiarity with fine-tuning and model evaluation techniques for large language models. • Strong command of object-oriented programming principles with expert knowledge of Java or C#, and Python. • Proficiency with relevant frameworks and libraries such as Spring Boot, .NET Core, TensorFlow, PyTorch , LangChain , Hugging Face Transformers, and OpenAI/Anthropic SDKs. • Experience in model lifecycle management, including training, deployment, monitoring, and retraining. • Skilled in MLOps practices: CI/CD for ML, model versioning, drift detection, and governance. • Knowledge of cost optimization strategies for LLMs in production environments. • Expert in distributed software patterns (DDD, microservices, serverless, event-driven) and cloud-native architectures (AWS, Azure, GCP). • Experience building monitoring, alerting, and observability for maintaining high SLAs in SaaS products. • Proficient in applying data security, compliance, and responsible AI principles across the solution lifecycle. • Promote inner-sourced tooling and shared technology standards across teams. • Leverage AI tools and practices to enhance engineering productivity, decision-making, and innovation. Benefits: • Flexible work environment • Medical, dental, vision, life and disability insurance • 401(k) Retirement Plan • Flexible Spending & Health Savings Account • Paid holidays, vacation, and volunteer time • Employee assistance program and other benefits
This job posting was last updated on 10/21/2025