Senior AI/ML Engineer
– LLM Agent Orchestration & MCP
Location:
Fully Remote – U.S.
Contract Duration:
12 months
About the Opportunity
Our client, Avalara - AI/ML team is building and scaling Avalara Aviator, a unified AI agent hub for tax and compliance, along with the Avalara Avi Agent (AAA) orchestration backbone.
We are seeking a
Senior AI/ML Engineer
with hands-on experience building production-grade LLM applications, multi-agent orchestration systems, Model Context Protocol (MCP) integrations, and automated evaluation pipelines.
In this role, you will design high-performance asynchronous services, integrate domain-specific tools across Avalara's tax products, and develop evaluation frameworks that ensure AI agents operate reliably, efficiently, and consistently in high-concurrency production environments.
What You'll Do
LLM Agent Orchestration & Backend Development
Design, implement, and optimize multi-agent orchestration workflows, including Agent-to-Agent (A2A) interactions, prompt templating, dynamic intent routing, and conversation memory.
Build high-performance asynchronous services using Python, asyncio, and FastAPI.
Develop scalable backend APIs and workflows supporting production AI applications.
MCP & Tool Integration
Standardize and integrate Model Context Protocol (MCP) servers and tools across Avalara products, including AvaTax, Returns, Tax Research, ECM, and Licensing.
LLM Evaluation & Benchmarking
Build automated evaluation pipelines using LLM-as-a-judge approaches, deterministic assertions, and evaluation harnesses.
Feature Gating & Entitlement Management
Implement cohort-based feature gating and entitlement evaluation for controlled beta rollouts.
Performance, Reliability & Observability
Optimize token consumption, response streaming, context caching, rate limiting, and error handling.
Engineering Excellence
Develop unit and integration tests and support CI/CD automation.
Maintain clear API documentation and technical documentation.
Collaborate with cross-functional teams in an Agile engineering environment.
Required Qualifications
5+ years of professional software engineering experience, with strong hands-on Python development expertise.
Strong experience building high-throughput asynchronous services using asyncio, FastAPI, or comparable technologies.
2+ years of hands-on experience developing production LLM applications, agentic workflows, function calling, tool use, or multi-agent systems.
Experience with agent frameworks such as LangChain, LangGraph, LlamaIndex, or custom orchestration frameworks.
Solid understanding of Model Context Protocol (MCP), RESTful API design, Agent-to-Agent (A2A) orchestration, and RAG or knowledge graph patterns.
Apply Now!