AI Data Architect

Role Overview: You are being sought after for the position of AI Data Architect with 12+ years of experience to take charge of designing and implementing scalable AI and LLM-driven systems, particularly focusing on chatbots and agent-based systems. Your role will entail ensuring the efficiency, optimal performance, and security of production-grade AI applications. The ideal candidate will possess in-depth knowledge in developing enterprise AI platforms, integrating data ecosystems, and establishing best practices for robust and responsible AI development. Key Responsibilities: - Design and deliver production AI / LLM / chatbot / agent systems - Define architecture for scalable, multi-service AI applications - Optimize LLM cost, latency, and throughput in real-world deployments - Integrate structured data platforms, APIs, and data warehouses into chatbot / agent workflows (not limited to RAG use cases) - Design testing, evaluation, and validation strategies for LLM-based systems - Implement rate limiting, throttling, quota management, and cost controls - Engage in prompt engineering, system prompt design, and agent/tool orchestration - Build multi-step / multi-agent / tool-calling AI workflows - Ensure observability, logging, tracing, token tracking, and cost monitoring for AI systems - Mitigate hallucinations, prompt injection, unsafe output, and data leakage - Implement security controls, RBAC, and data access boundaries in AI applications - Collaborate with multiple model providers and select models based on cost / latency / quality / reliability tradeoffs - Design high-performance backend services supporting AI workloads - Utilize caching, batching, async processing, and parallel execution patterns - Deploy AI systems in cloud environments with CI/CD, feature flags, and staged rollout - Work with engineering teams to define standards, guardrails, and best practices for AI development Qualifications Required: - Experience leading or advising teams building enterprise AI platforms - Familiarity with agent frameworks / orchestration frameworks - Proficiency with LLM evaluation frameworks and automated scoring - Ability to design governance and usage policies for AI systems - Experience handling large-scale usage where cost management is crucial - Proficiency in supporting customer-facing AI features in production - Skilled in debugging complex behavior across prompts, tools, models, and data sources Additional Details (If Applicable): The company, Persistent, is committed to fostering diversity and inclusion in the workplace. They encourage applications from all qualified individuals, regardless of disabilities, gender, or gender preference. The organization supports hybrid work and flexible hours to accommodate diverse lifestyles. The office is designed to be accessibility-friendly, with ergonomic setups and assistive technologies to support employees with physical disabilities. If you have specific requirements due to disabilities, you are encouraged to inform the company during the application process or at any point during your employment. Role Overview: You are being sought after for the position of AI Data Architect with 12+ years of experience to take charge of designing and implementing scalable AI and LLM-driven systems, particularly focusing on chatbots and agent-based systems. Your role will entail ensuring the efficiency, optimal performance, and security of production-grade AI applications. The ideal candidate will possess in-depth knowledge in developing enterprise AI platforms, integrating data ecosystems, and establishing best practices for robust and responsible AI development. Key Responsibilities: - Design and deliver production AI / LLM / chatbot / agent systems - Define architecture for scalable, multi-service AI applications - Optimize LLM cost, latency, and throughput in real-world deployments - Integrate structured data platforms, APIs, and data warehouses into chatbot / agent workflows (not limited to RAG use cases) - Design testing, evaluation, and validation strategies for LLM-based systems - Implement rate limiting, throttling, quota management, and cost controls - Engage in prompt engineering, system prompt design, and agent/tool orchestration - Build multi-step / multi-agent / tool-calling AI workflows - Ensure observability, logging, tracing, token tracking, and cost monitoring for AI systems - Mitigate hallucinations, prompt injection, unsafe output, and data leakage - Implement security controls, RBAC, and data access boundaries in AI applications - Collaborate with multiple model providers and select models based on cost / latency / quality / reliability tradeoffs - Design high-performance backend services supporting AI workloads - Utilize caching, batching, async processing, and parallel execution patterns - Deploy AI systems in cloud environments with CI/CD, feature flags, and staged rollout - Work with engineering teams to define standards, guardrails, and best pract