Position Summary

GEICO is seeking an experienced Sr. Software Engineer to join our Unified Communications Service Engineering (UCSE) group and lead the development of cutting-edge AI product development. This role is ideal for candidates with deep expertise in building products powered by AI models, with a particular focus on working with large language models (LLMs). You will help drive our insurance business transformation as we transition from a traditional IT model to a tech organization by designing, developing, and deploying core consumer experiences that leverage AI, ensuring they are robust, scalable and production ready. 

Position Description

The Unified Communication Service Engineering team is transitioning disparate customer communication touchpoints into a world class services company by building the foundational voice, chat, text, email and core contact center experiences for sales, service and claims operations used by 20,000 GEICO contact center agents, field adjusters and sales representatives sell, endorse, and service more than 80 million customers and prospective customers.

Our Sr. Software Engineer is a lead member of the engineering team working across the organization to build delightful and friction-less product experience for our customers and drive transformative change in the industry by harnessing the power of Generative AI. Our team thrives and succeeds in delivering high-quality products and services in a hyper-growth environment where priorities shift quickly. The ideal candidate has broad and deep technical knowledge, typically ranging from front-end UIs through back-end systems and all points in between.

Position Responsibilities

As a Senior Engineer - Applied AI, you will:

• Identify AI opportunities: Evaluate and prioritize opportunities to automate business processes using AI, intelligent workflows, and agent-based systems.

• Design and ship applied AI solutions: Architect, build, and deploy AI solutions for high-value workflows including automation, document intelligence, decision support, and intelligent assistants.

• Build agentic workflows: Design and implement AI agents and agentic workflows that orchestrate tools, APIs, reasoning steps, and business logic to automate complex processes at scale.

• Own production systems end-to-end: Develop, deploy, and operate services that meet high standards for scalability, resilience, performance, security, and availability, taking ownership from design through production support.

• Leverage knowledge graphs: Use knowledge graphs to enhance reasoning, entity relationships, context retrieval, and multi-step workflows.

• Partner across functions: Collaborate with product, engineering, operations, and analytics partners to co-create scalable AI solutions and translate business needs into robust technical designs.

• Mentor and upskill others: Coach engineers and scientists in AI, LLMs, and agentic workflow design through pairing, reviews, and architectural guidance.

• Drive innovation: Explore new models, frameworks, and reasoning techniques and apply them thoughtfully to real-world challenges.

• Influence architecture: Provide technical guidance on architecture, experimentation, and deployment within and across teams.

• Experiment and evaluate rigorously: Run end-to-end experimentation, including hypothesis definition, measurement, validation, and iterative improvement in production environments.

• Model best practices: Establish and promote engineering best practices for reliability, interpretability, safety, governance, and monitoring of production AI systems.

What We Are Looking For (Must Have)

• Experience: 4+ years of professional software engineering or applied machine learning experience, including 1+ years working with Generative AI or LLM-based systems in production.

• Hands-on AI engineering: Strong experience with Python and modern AI frameworks such as LangChain, LangGraph, LangSmith, LlamaIndex, Hugging Face, and OpenAI or Anthropic APIs.

• Production AI delivery: Demonstrated experience designing, building, and operating production AI systems, including agentic workflows and intelligent automation features.

• Systems engineering excellence: Proven track record building scalable, resilient, secure, and maintainable systems that run reliably in production.

• AI & data architectures: Strong understanding of agent architectures, workflow orchestration, retrieval-augmented generation, vector databases, and knowledge graph integration.

• Cross-functional collaboration: Ability to work deeply with engineers, product managers, and domain experts to co-create solutions.

• Mentorship: Experience mentoring engineers and helping others grow in AI, LLM, and agent-based system design.

• Business impact: History of delivering measurable business outcomes with AI solutions.

• Distributed systems fundamentals: Solid competency in distributed systems, service design, performance optimization, and reliability engineering.

Nice to Have

• Advanced GenAI capabilities: Experience building domain-tuned LLMs, vector reasoning techniques, or specialized retrieval architectures.

• Regulated domains: Experience in insurance, financial services, or other regulated industries.

• Java ecosystem: Experience deploying AI components in Java ecosystems (e.g., Spring AI, LangChain4j, Embabel).

• Deep domain modeling: Background in document intelligence, fraud or anomaly detection, or complex ontology and knowledge graph design.

• AI safety & governance: Familiarity with AI safety practices, evaluation frameworks, monitoring, and regulatory compliance.

• Executive communication: Ability to clearly communicate complex technical topics to senior leadership and non-technical stakeholders.

Education

• Bachelor27s degree in Computer Science, Information Systems, or equivalent education or work experience