GEICO's AI Agent Platform team is seeking a Senior Staff Software Engineer to build the next generation enterprise Agent OS and SDKs, enabling business, product, and engineering teams to build, test, and deploy their own AI agents & workflows.
Requirements
- 10+ years of hands-on experience in designing, implementing, and maintaining multi-tenant AIML systems and platforms in production environments.
- 10+ years of experience working with cloud platforms such as Azure and AWS.
- Extensive expertise in designing and deploying large-scale data pipelines and real-time inference systems and managing the end-to- end AI Agent and/or AIML system development lifecycles, including configuration, evaluation, monitoring, observability and AuthN/AuthR considerations
- 8+ years of experience working with common backend systems & tools (e.g, Kubernetes, Temporal, OpenSearch, PostgreSQL, Redis, Neo4J, etc.). Deep understanding of Docker, container optimization, and multi- stage builds. Experience with Prometheus, Grafana, Open Telemetry and distributed tracing
- 4+ years of experience building front-end web applications using frameworks such as React and/or Next.JS
- Deep proficiency in programming languages such as Python, Java, Go, etc., with a strong emphasis on coding excellence.
- Proficiency in AIML frameworks such as TensorFlow, PyTorch, Langraph, etc.
Responsibilities
- Architect and implement scalable multi-tenant backend systems for building AI agent workflows, including agent configuration, offline evaluation, synthetic data generation, workflow simulation, agent marketplace, etc. using Azure Kubernetes Service (AKS), FastAPI, etc., ensuring economy of scale and control cost of maintenance.
- Collaborate with Design team to architect and implement frontend experiences and workflows for onboarding both technical and non- technical stakeholders, maximizing user adoption and successful AI agent development
- Develop observability frameworks to ensure 99.9%+ uptime for AI agent platforms through robust monitoring, alerting, and incident response procedures
- Evaluate and (if desirable) integrate cutting-edge GenAI frameworks, libraries and vendors to maintain a state-of-the-art technology stack, including hybrid cloud solutions with AWS/GCP as backup or specialized use cases
- Architect and implement scalable, high-performance machine learning platforms and systems capable of processing large data volumes and supporting real-time decision making and workflows.
- Oversee the end-to-end lifecycle of AI agent applications, ensuring robust testing, deployment, and ongoing monitoring.
- Design and maintain robust CI/CD pipelines for ML model deployment using Azure DevOps, GitHub Actions, and MLOps tools
Other
- Act as the tech lead across multiple sub-teams/initiatives, setting technical direction and ensuring consistency in design principles and best practices.
- Provide hands-on mentorship and guidance during design reviews, code assessments, and performance tuning.
- Lead by example in tackling complex technical challenges and driving system-wide architectural improvements.
- Work closely with data scientists, software engineers, and product teams to seamlessly deploy ML systems into production environments.
- Translate complex technical concepts into actionable insights for both technical and non-technical stakeholders.
