Senior Machine Learning Engineer, CX

Architect and deploy the multi-agent framework used for agent assist, internal SOP execution, and secure LLM-powered actions, building scalable systems able to handle millions of customer interactions.

Own end-to-end execution of complex ML initiatives, managing priorities, technical trade-offs, and cross-functional dependencies from design through production delivery.

Build and optimize AI-driven concierge chat and agent copilot experiences that improve automated resolution rates and reduce case handling time.

Develop systems to detect and manage bad actors and adversarial inputs, keeping the multi-agent platform safe and reliable at scale.

Establish best practices for system design, coding standards, and evaluation frameworks for ML/AI systems, and mentor team members on architectural decisions and modern ML development workflows.

5+ years of professional experience in machine learning and software engineering, with a track record of shipping production-grade ML services at scale.

Hands-on expertise with large language models, deep learning architectures, and the generative AI ecosystem (LangGraph, LangSmith, Google ADK, Vertex AI, or AWS Bedrock), with demonstrated ability to build multi-agent or LLM orchestration systems.

Proficiency in Python, with the ability to write clean, maintainable, and well-tested production code for ML applications.

Specialized depth in at least one domain — NLP, information retrieval, conversational AI, or advanced statistical modeling — along with the ability to ramp up quickly in adjacent areas.

Proven ability to write technical design documents and communicate complex ML concepts clearly to non-technical stakeholders across product, design, and CX teams.

A track record of using generative AI responsibly, maintaining human oversight to deliver business-ready outputs and drive measurable improvements in workflow efficiency, cost, and quality.

Demonstrated ability to responsibly use generative AI tools and copilots (e.g., LibreChat, Gemini, Glean) in daily workflows, continuously learning as tools evolve, and applying human-in-the-loop practices to deliver business-ready outputs and measurable improvements in efficiency, cost, and quality.