Sr Software Engineer- AI

Overview

At GEICO, we offer a rewarding career where your ambitions are met with endless possibilities.

Every day we honor our iconic brand by offering quality coverage to millions of customers and being there when they need us most. We thrive through relentless innovation to exceed our customers’ expectations while making a real impact for our company through our shared purpose.

When you join our company, we want you to feel valued, supported and proud to work here. That’s why we offer The GEICO Pledge:
Great Company, Great Culture, Great Rewards and Great Careers.

GEICO is seeking an experienced Engineer with a passion for building high-performance, low maintenance, zero-downtime platforms, and applications. You will help drive our insurance business transformation as we transition from a traditional IT model to a tech organization with engineering excellence as its mission, while co-creating the culture of psychological safety and continuous improvement.

The Senior Staff Engineer in Availability and Incident Management will design and deploy machine learning systems that enable intelligent incident detection, automated root cause analysis, and predictive reliability improvements across the platform. This role focuses on building a multi-agent AI platform where specialized agents autonomously detect anomalies, diagnose failures, recommend remediation actions, and learn from historical patterns to prevent recurring incidents.

You will lead the technical strategy for an AI-powered incident response system that reduces mean time to resolution, minimizes operational toil, and enables proactive reliability improvements through predictive analytics and autonomous workflows. The ideal candidate combines deep expertise in machine learning systems, agentic AI, and multi-agent architectures with strong knowledge of site reliability engineering, observability tooling, and large-scale distributed systems.

As a Senior Staff Engineer, you will:

• Design and build a multi-agent AI platform where specialized agents autonomously detect, diagnose, and resolve issues through agent-to-agent (A2A) collaboration
• Develop intelligent agents using LLMs and agentic frameworks that coordinate detection, diagnostic, remediation, and knowledge tasks with minimal human intervention
• Define agent interaction protocols, A2A communication standards, and evaluation frameworks for agent decision quality and autonomous action safety
• Architect vector database solutions (Milvus, pgvector, Qdrant) for semantic search and RAG to enable context-aware agent decision-making
• Build end-to-end ML pipelines for severity classification, anomaly detection, failure pattern recognition, and impact forecasting using observability data
• Establish scalable orchestration infrastructure for multi-agent workflows with CI/CD, automated evaluation, canary releases, and rollback strategies
• Implement monitoring for agent interactions, A2A communication patterns, decision quality, data drift, and system reliability
• Lead technical architecture ensuring scalability, observability, and integration with existing alerting, logging, and monitoring systems
• Define standards for agent safety, explainability, governance, and human-in-the-loop controls for high-impact automated actions
• Partner with SRE, Product, and Engineering teams to translate reliability goals into measurable ML objectives and maintain pragmatic technical roadmaps
• Mentor engineers through complex AI platform implementations and establish best practices, coding standards, and technical documentation
• Stay current with AI/ML and multi-agent systems; educate engineering leadership on emerging technologies

• Experience building and deploying ML systems in production with cross-functional engineering teams
• Fluency in at least two modern languages such as Python, Go, Java, C++, or C# including object-oriented design
• Experience architecting multi-component ML platforms using open-source/cloud-agnostic components:
  • Data stores:
    Postgre
    
    SQL, No
    
    SQL (Mongo
    
    DB, Cassandra, Cosmos
    
    DB)
  • Streaming:
    Kafka, Flink, or Spark Streaming
• Experience with end-to-end ML lifecycle: version control, CI/CD, Kubernetes, testing, monitoring, and production support
• Experience with cloud providers (Azure, AWS or GCP) in production ML environments
• Experience with observability tools and distributed systems monitoring, logging, tracing, and root cause analysis
• Experience building multi-agent systems using LLMs and agentic frameworks (e.g., Lang Chain, Lang Graph, Auto Gen, Semantic Kernel, CrewAI)
• Hands-on experience with RAG, semantic search, and vector databases (e.g., Milvus, pgvector, Qdrant, Elastic Search)
• Experience designing human-in-the-loop workflows and safety controls for autonomous systems
• Strong architecture and design skills with ability to influence technical direction and roadmap
• Proven ability to solve complex problems with data-driven approaches
• Experience fine-tuning or deploying…