Senior Engineer, Interactive Voice Response - AI/ML

GEICO•Palo Alto, CA

About The Position

GEICO's Service Engineering team is revolutionizing customer service using AI and multi-agent systems. This role is perfect for someone passionate about creating large-scale, distributed AI applications with significant business impact, focusing on enhancing self-service rates across all communication channels, from voice (IVR) to chat. The Senior Engineer will be a leading member of the engineering staff, working across the organization to provide a frictionless experience for customers while maintaining the highest standards of protection and availability. The team thrives in a hyper-growth environment where priorities shift quickly, requiring broad and deep technical knowledge from front-end UIs through back-end systems.

Requirements

Hands-on proficiency with modern AI/ML frameworks and tools (e.g., TensorFlow, PyTorch) and programming languages such as Python, Java, or C++.
Proven experience designing, developing, and deploying AI or machine learning models (LLMs) in production environments, with a focus on scalability and performance.
Strong software engineering background with expertise in building large-scale distributed systems, preferably in cloud environment (Azure or AWS).
Demonstrated ability to apply AI/ML solutions to real-world business problems, delivering measurable impact in areas such as natural language processing, speech recognition, recommendation systems, or intelligent automation.
Experience in building products using micro-service-oriented architecture and extensible REST APIs.
Experience building the architecture and design (architecture, design patterns, reliability, and scaling) of new and current systems.
Experience with continuous delivery and infrastructure as code.
Experience in leveraging PowerShell scripting.
Experience in existing Operational Portals such as Azure Portal.
Experience with application monitoring tools and performance assessments.
Ability to excel in a fast-paced, startup-like environment.
Knowledge of developer tooling across the software development life cycle (task management, source code, building, deployment, operations, real-time communication).
4+ years of professional software development experience within a Python or Java framework (J2EE, web containers and Java).
4+ years of experience in open-source frameworks.
3+ years of experience with architecture and design.
3+ years of experience with AWS, GCP, Azure, or another cloud service.
Bachelor’s degree in computer science, Information Systems, or equivalent education or work experience.

Responsibilities

Design, develop, and deploy large-scale distributed AI applications that power customer self-service across multiple communication channels (voice, IVR, chat).
Build and optimize multi-agent systems that enable intelligent, collaborative decision-making to improve automation and customer experience.
Collaborate with cross-functional teams (engineering, product, data science) to translate business requirements into scalable AI/ML solutions.
Ensure system reliability, scalability, and performance through best practices in architecture, testing, and monitoring.
Stay at the forefront of AI and distribute systems research, bringing innovative approaches and tools into production environment.
Utilize programming languages like Python, SQL, and NoSQL databases, Container Orchestration services including Docker and Kubernetes, and a variety of Azure tools and services.
Consistently share best practices and improve processes within and across teams.