Machine Learning Engineer V

Avalara is accelerating an AI-first transformation, and they are seeking a Machine Learning Engineer V to help build and scale the Avalara Avi Agent. This role will focus on developing reliable, production-grade systems to improve automation and customer outcomes while establishing best practices for agentic applications.

Responsibilities:

• Design, build, and operate foundational agentic platform capabilities that enable Aviator, AAA, and other Avalara agentic experiences to move from prototype to production
• Develop scalable LLM application frameworks, orchestration patterns, tool integrations, and agent workflows that support enterprise-grade reliability, observability, security, and maintainability
• Create and improve evaluation methods for agentic outcomes, including quality, accuracy, latency, cost, safety, and task-completion effectiveness
• Translate ambiguous business and product needs into technical designs, prototypes, production features, and measurable engineering outcomes
• Apply modern software engineering practices, including CI/CD, automated testing, code review, documentation, and operational readiness, to ensure high-quality delivery
• Partner with product, engineering, security, data, and business stakeholders to ensure agentic capabilities solve meaningful customer and operational problems
• Research, assess, and responsibly apply emerging AI technologies, including LLMs, model-context protocols, agent-to-agent patterns, retrieval, evaluation, and automation techniques
• Document reusable patterns and implementation guidance that help Avalara engineers and software agents build consistently, safely, and efficiently
• Mentor engineers and raise the technical bar through design reviews, code reviews, coaching, and examples of high-ownership execution
• Strengthen the operational robustness of mature high-availability systems while introducing new AI capabilities without compromising customer trust or production stability

Requirements:

• B.S. in Computer Science, Engineering, or a closely related technical field
• 8+ years of relevant professional experience building, deploying, and operating production software systems, with strong preference for Python experience
• Hands-on experience building LLM applications, agentic systems, or AI-enabled workflows in production or production-like environments
• Experience with LLMs such as GPT, Claude, Llama, or similar models, including practical understanding of prompting, orchestration, evaluation, and reliability considerations
• Experience with enterprise-scale software design, distributed systems, data structures, design patterns, and high-availability system operations
• Experience working in cloud computing environments such as AWS, Azure, or GCP
• Applied familiarity with modern agentic integration patterns and protocols, such as MCP, A2A, tool use, retrieval, and multi-agent orchestration
• Demonstrated ability to use AI to improve measurable outcomes, such as speed, quality, automation, insight, customer experience, or scale
• Strong communication, documentation, mentoring, and cross-functional collaboration skills