Senior AI Engineer

QXO•Seattle, WA

11d•$150,000 - $220,000

About The Position

QXO is a leading distributor and installer of building products serving an $800 billion market. The company’s mission is to modernize the building products industry through advanced technology and a best-in-class customer experience. QXO is North America’s largest distributor and installer of insulation, the second-largest distributor of roofing products, the second-largest publicly traded distributor of lumber and building materials, and the largest distributor of waterproofing products. The company is targeting $50 billion in annual revenue within the decade through accretive acquisitions and organic growth. For more information, visit QXO.com. We are seeking a highly skilled Senior Software Engineer, AI to design, build, and deploy production-grade AI agents that augment workflows across our organization. The ideal candidate has hands-on experience with agentic frameworks, MCP servers, LLM orchestration libraries, and robust testing/monitoring practices. This role blends software engineering excellence with applied machine learning and offers the opportunity to push the boundaries of intelligent automation in real business environments.

Requirements

3–7+ years of experience as a Software Engineer, Machine Learning Engineer, or AI Engineer (flexible based on seniority).
Proven experience building AI agents or LLM-driven applications in production contexts.
Hands-on work with libraries/frameworks such as LangChain, OpenAI/MCP, LlamaIndex, or similar orchestration tools.
Proficiency with Python (or Typescript/Node) and modern development workflows.
Experience integrating LLMs with external tools, APIs, vector databases, and retrieval systems.
Strong understanding of CI/CD, containerization (Docker), cloud deployment (AWS/GCP/Azure), and DevOps fundamentals.
Familiarity with automated testing approaches for LLM applications (unit tests, scenario testing, eval harnesses).
Excellent problem-solving skills and the ability to design resilient systems in ambiguous environments.

Nice To Haves

Experience deploying and scaling MCP servers, custom toolchains, or enterprise agent frameworks.
Prior work building tools or automations for Sales, Marketing, or RevOps teams (e.g., CRM-integrated apps, quoting tools, outbound tooling, marketing analytics or experimentation platforms).
Background or project experience in the building industry (construction, materials distribution, building automation, supply chain, procurement) or other B2B industry.
Experience with workflow engines (Airflow, Prefect, etc) and/or MLOps (Mlflow, Flyte, etc) and event-driven architectures.
Familiarity with vector and search/retrieval systems.
Understanding of prompt engineering, model fine-tuning, or RLHF-style evaluation frameworks.

Responsibilities

Architect, build, and optimize AI agents using modern agent frameworks (e.g., LangChain, LlamaIndex, OpenAI/MCP-based ecosystems, or equivalents).
Implement MCP (Model Context Protocol) servers, custom tools, and integrations to enable secure and scalable agent capabilities.
Design agentic workflows that can operate autonomously, perform multi-step reasoning, and interact with structured/unstructured data sources.
Package and deploy agents into production environments with attention to reliability, observability, and performance.
Build agents that support Sales Representatives, such as: Lead and account research, enrichment, and prioritization; Drafting and personalizing outbound emails and sequences; Summarizing calls, meetings, and account activity to drive next-best actions; Integrating with CRM and sales tools (e.g., Salesforce, HubSpot, Outreach) to automate data entry and insight surfacing; Generating detailed bills of materials (BOMs), estimates, and quotes from drawings, specs, takeoffs, or CRM/opportunity data, including price checks, margin validation, and versioning.
Build agents that support Marketing, such as: Generating and localizing content for campaigns, landing pages, and nurture programs; Assisting with audience segmentation, experimentation, and performance analysis; Powering internal “marketing copilots” that answer questions from campaign, web, and analytics data.
Partner with the business to identify high-ROI workflows for automation and to measure the impact of deployed agents on pipeline, conversion, quoting speed/accuracy, and engagement metrics.
Develop internal libraries, reusable modules, and standardized patterns for building agentic applications.
Integrate agent systems with enterprise APIs, cloud services, databases, pricing/catalog systems, and operational infrastructure.
Build CI/CD pipelines for both model-related code and agent-specific behavior, including automated testing, evaluation harnesses, and regression detection for LLM-powered systems.
Create frameworks for continuous evaluation of agents, including prompt tests, scenario simulations, and safety/robustness checks.
Monitor agent performance in production, diagnose failures, and iterate quickly on improvements.
Implement logging, analytics, and feedback loops to guide ongoing training or refinement—especially for critical revenue and quoting workflows.
Work closely with product, engineering, Sales, Marketing, and domain experts to translate business processes into agentic flows.
Partner with stakeholders to identify automation opportunities and design AI-powered operational solutions.
Contribute to internal documentation, best practices, and AI engineering guidelines.