Staff Software Engineer, AI Agent Platform

GEICO • New York City, MD

2d

About The Position

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. The G eico AI Agent Platform team is seeking an exceptional Staff Software Engineer to build the next generati on enterprise Agent OS and SDKs . This role combines deep technical expertise in platform engineering , application design and agentic workflows with strong leadership and mentoring capabilities. You will be responsible for designing, implementing, and maintaining scalable, reliable frontend and backend systems that enable our business, product and engineering teams to build, test and deploy their own AI agen ts & workflows . The candidate must have excellent communication skills and a proven track record of delivering business value via technical excellence .

Requirements

• Bachelor’s degree in computer science , Engineering , Mathematics, or a related field; an advanced degree (master’s or Ph.D.) is highly desirable.
• 6 + years of hands-on experience in designing, implementing, and maintaining multi-tenant AIML systems and platforms in production environments.
• 6 + 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
• 6 + years of experience working with common backend systems & tools ( e.g , Kubernetes, Temporal, OpenSearch , PostgreSQL , Redis, N eo4J, etc.) .
• Deep understanding of Docker, container optimization, and multi-stage builds .
• Experience with Prometheus, Grafana , Open Telemetry and distributed tracing
• 3 + 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.
• Extra credit for properly leveraging AI coding tools such as Cursor for productivity gains
• Proficiency in AIML frameworks such as TensorFlow, PyTorch , Langraph , etc.
• Demonstrated track record of mentoring engineers and leading technical initiatives
• Proven ability to tackle complex technical challenges, innovate through hands-on experimentation, and set technical standards.
• Excellent verbal and written communication against audience of diverse seniority levels and professional backgrounds

Nice To Haves

• Deep expertise operating and/or building AI agent platforms & capabilities like Langraph platform, Autogen , N8N, Crew.ai , etc.
• Experience with LLM observability systems such as Langsmith , Langfuse , Arize Phoenix, etc.
• Experience building LLM-based AI agent workflows via both no code/low code and traditional high-code development environments
• Experience utilizing both open source (e.g. llama, Qwen, Mistral) and proprietary (e.g. GPT, Claude) LLMs for appropriate tasks
• Understanding of AI safety principles, model governance, and regulatory compliance
• Background in regulated industries with understanding of data privacy requirements and cybersecurity review processes

Responsibilities

• Platform Engineering : 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 e nsure 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.
• DevOps/ Application Lifecycle Management: Oversee the end-to-end lifecycle of AI agent applications , ensuring robust testing, deployment, and ongoing monitoring.
• Ensure adherence to company production readiness standards, security protocols, and regulatory compliance throughout the development lifecycle.
• Continuously optimize platform performance, reducing latency and improving throughput for AI agent workloads
• Design and implement backup, recovery, and business continuity plans for hosted platform applications & services
• Design and maintain robust CI/CD pipelines for ML model deployment using Azure DevOps, GitHub Actions, and MLOps tools
• Technical Leadership : Act as the tech lead for a sub-team , 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.
• Establish and champion engineering standards for ML infrastructure, deployment practices, and operational procedures
• Create technical documentation, runbooks, and deliver internal training sessions on platform capabilities
• Cross-Functional Collaboration: 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.
• Foster a collaborative environment that encourages innovation and the sharing of best practices across teams.
• Present technical solutions and platform roadmaps to leadership and cross-functional stakeholders

Benefits

• Financial benefits including market-competitive compensation; a 401K savings plan vested from day one that offers a 6% match; performance and recognition-based incentives; and tuition assistance.
• Access to additional benefits like mental healthcare as well as fertility and adoption assistance.
• Supports flexibility- We provide workplace flexibility as well as our GEICO Flex program, which offers the ability to work from anywhere in the US for up to four weeks per year.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees