Responsibilities
- Lead the full lifecycle architecture design for a Conversational AI and Knowledge platform, including AI model integration, data storage, knowledge bases, and third-party connections.
- Create cloud-native, microservices-based systems built for enterprise scale, supporting high concurrency, traffic bursts, and real-time interactions.
- Develop streamlined, cost-efficient architectures using native AWS services, prioritizing scalability and fault tolerance without unnecessary complexity.
- Establish reference models, architectural templates, and non-functional requirements focused on performance, reliability, security, and ease of maintenance.
- Implement event-driven and asynchronous system designs using AWS tools such as SQS, SNS, EventBridge, and Step Functions.
- Set standards for microservices, domain-driven design, API development (REST and event-based), and AI integration patterns.
- Evaluate and guide complex application designs, critical code paths, and AI processing pipelines.
- Design and enhance AI-powered conversational systems using large language models, prompt engineering, and enterprise AI orchestration frameworks.
- Build and evolve knowledge management solutions using AWS Knowledge Hub, vector databases, RAG architectures, and related technologies.
- Define strategies for integrating AI models, including selection, fine-tuning, embedding workflows, and quality assessment frameworks.
- Shape the architecture of conversational user experiences to ensure low latency, context awareness, and seamless interaction flows.
- Assess and recommend AI platforms and tools—such as AWS Bedrock, LangChain, OpenAI, Anthropic, Kore.ai, and Dialogflow—based on business needs.
- Lead the design of systems managing multi-turn conversations, intent recognition, and fallback logic.
- Architect and optimize solutions using AWS services including Lambda, API Gateway, SQS, SNS, Step Functions, DynamoDB, Aurora Serverless, S3, Bedrock, and Kendra.
- Design scalable, cost-effective infrastructure strategies to handle variable conversational AI workloads.
- Oversee cloud governance, environment separation, multi-account structures, and infrastructure-as-code practices.
- Define standards for CI/CD pipelines, DevOps processes, and containerization (Docker, Kubernetes) for deploying AI workloads.
- Guide microservices decomposition, defining service boundaries, communication patterns, and data ownership.
- Engineer systems for extreme scale, supporting high user concurrency, transaction rates, and real-time AI inference.
- Own resilience planning, including multi-AZ and multi-region setups, active-active or active-passive disaster recovery, and graceful degradation.
- Define and validate recovery point and recovery time objectives, conduct chaos engineering tests, and lead disaster recovery exercises.
- Ensure zero-downtime deployments using blue/green, canary, and rolling deployment methods.
- Integrate security principles across all layers of AI and data architecture, covering access control, encryption, data privacy, and model safety.
- Support compliance with SOC2, ISO, and GDPR standards, particularly in AI data handling and knowledge base access controls.
- Collaborate with SRE and DevOps teams to implement observability, logging, distributed tracing, and alerting for AI systems.
Benefits
- Be part of a growing, innovative global organization where top-tier teams operate in a dynamic, collaborative, and creative environment.
- Work in a market-leading environment offering continuous learning, growth, and diverse internal career paths across roles, disciplines, and regions.
- Enjoy NiCE-FLEX, a hybrid work model allowing 2 office days and 3 remote days weekly, fostering collaboration and innovation while supporting flexibility.
Work Arrangement
Hybrid
Team
Reports to: Director, Engineering
Other
Requisition ID: 10787
