Distinguished Engineer, AI Applications

Key Responsibilities 

Enterprise Architecture & Technical Authority 

• Define, own, and evolve the foundational architecture for GEICO’s Generative AI and agentic workflow platforms. 

• Serve as a final technical authority on complex architectural decisions impacting multiple products, teams, and business domains. 

• Design interconnected, high-performance, and durable platform components that power end-to-end GenAI workflows, including:  

• Knowledge curation and management 

• Search and retrieval systems 

• Prompt and context management 

• Workflow orchestration and action execution 

• Semantic and knowledge graph systems 

Platform & GenAI Applications Strategy, Architecture, and Business Impact 

• Establish and drive multi-year technical strategy and roadmaps for both AI platform capabilities and Generative AI (GenAI) applications in close partnership with product and business leaders. 

• Balance speed, scalability, reliability, and extensibility while ensuring platforms and GenAI applications can support future AI use cases, evolving business needs, and organizational growth. 

• Influence investment decisions by evaluating build vs. buy tradeoffs and architectural choices for both the underlying platform and GenAI applications. 

• Define the reference architecture and best practices for GenAI application development, deployment, and integration, ensuring alignment with overall enterprise architecture. 

• Collaborate with business stakeholders to identify high-impact GenAI application opportunities and develop strategies to maximize business value and measurable outcomes. 

• Continuously assess and communicate the business impact of GenAI applications, providing clear metrics and feedback loops to inform ongoing strategy and platform evolution. 

System & Technology Evaluation 

• Lead evaluation and selection of core technologies, frameworks, and infrastructure components with a emphasis on building and scaling Generative AI applications, including LLM orchestration(e.g., LangChain, LlamaIndex), agentic workflows, RAG systems, and evaluation/observability tooling, while partnering on underling AI platform infrastructure and services to support production readiness.  

• Ensure architectural consistency and technical rigor across open-source, cloud-agnostic, and managed service integrations. 

Cross-Organization Influence 

• Collaborate across engineering, data science, ML, product, and design organizations to align on platform and GenAI application direction, technical standards, and business objectives. 

• Drive alignment across teams by translating complex technical and business concepts into clear architectural guidance and decision frameworks. 

• Partner with senior technical and business leaders across departments to promote enterprise-wide adoption of GenAI best practices and maximize organizational impact. 

Technical Leadership & Problem Solving 

• Tackle the most complex and ambiguous technical and business challenges affecting system-wide and application-specific performance, reliability, and scalability. 

• Lead deep technical reviews, architectural assessments, and design discussions for critical AI and GenAI application initiatives. 

• Guide platform and GenAI application evolution through hands-on engagement when necessary, especially in high-impact or high-risk areas. 

Mentorship & Technical Stewardship 

• Mentor senior engineers and technical leads, setting a high bar for architectural thinking, engineering quality, and technical decision-making for both platform and GenAI application initiatives. 

• Establish and reinforce best practices for platform and GenAI application design, reliability, observability, and operational excellence. 

• Contribute to internal documentation, architectural standards, and technical knowledge sharing for both the AI platform and GenAI applications. 

Minimum Qualifications 

• Master’s degree or higher in Computer Science, Engineering, Statistics, or a related field. 

• 10+ years of professional software engineering experience, with deep expertise in large-scale distributed systems. 

• Extensive experience architecting and building multi-component AI/ML platforms using technologies such as:  

• Search and retrieval systems (e.g., Elasticsearch, Qdrant, Milvus, Pinecone,Weaviate) 

• Data platforms (e.g., Snowflake, relational and NoSQL databases, and feature stores) 

• Streaming and distributed processing (e.g., Kafka, Spark, Ray) 

• Workflow orchestration (e.g., Airflow, Temporal, Prefect) 

• LLM orchestration and application frameworks ( e.g., LangChain, Llamaindex) 

• Observability, evaluation, and tracing for GenAI systems (e.g., LangSmith, Arize Phoenix, Weights & Biases, OpenTelemetry) 

• Vector databases, embedding pipelines, and retrieval-augmented generation (RAG) architectures 

• Agentic frameworks and multi-agent systems for complex task execution 

• Strong background in full software development lifecycle ownership, including CI/CD, Kubernetes, monitoring, and production operations. 

• Deep experience with major cloud platforms such as AWS and Azure. 

• Demonstrated hands-on experience building production systems using LLMs and Generative AI technologies (e.g., GPT, Llama, Mistral, Claude) to power conversational and agentic workflows.