• Design and implement end-to-end AI systems, integrating foundation models into various applications and workflows. • Apply and optimize model adaptation techniques, including prompt engineering, Retrieval-Augmented Generation (RAG), and finetuning, to tailor foundation models for specific use cases. • Develop and integrate AI architecture components such as context enhancement, input/output guardrails, model routers/gateways, caching mechanisms, and agent patterns to ensure system reliability and security. • Implement AI pipeline orchestration to define and chain together different components of an AI system, ensuring seamless data flow and complex workflow execution. • Optimize AI model inference for latency and cost, utilizing techniques like quantization, distillation, and parallelism, and demonstrate proficiency in working with GPUs and large compute clusters. • Collaborate closely with Data Scientists to integrate trained models and with Data Engineers to ensure efficient data pipelines for AI applications. • Contribute to defining and implementing systematic evaluation pipelines for AI applications, focusing on metrics such as factual consistency, generation capability, and instruction-following for open-ended outputs. • Engage in continuous monitoring and observability of AI systems in production to detect failures, drifts, and identify opportunities for improvement and cost savings. • Assist in productizing AI-powered outputs and features, ensuring alignment with customer needs and product strategy.

• Lead the design, development, and scalability of core Java-based backend services that power our multi-tenant platform. • Architect and optimize platform components to support high-throughput, low-latency, and mission-critical workflows. • Integrate and manage core data systems (e.g., relational DBs, Redis, Elasticsearch, LDAP) to ensure performance, availability, and fault tolerance. • Drive the modernization of backend services, refactoring legacy Java components and adopting modern patterns (e.g., reactive programming, event-driven architectures). • Champion best practices for Java development, testing, observability, and deployment in a distributed, microservices-based environment. • Collaborate cross-functionally with teams across DevOps, Security, SRE, and Application Engineering to build robust platform capabilities. • Evaluate and implement scalable solutions for authentication, authorization, tenant isolation, and configuration management. • Mentor engineers across teams in deep Java design principles, debugging complex issues, and engineering for reliability. • Develop and maintain platform APIs, service orchestration logic, and critical workflows that support core business operations. • Identify and remediate bottlenecks in Java services, JVM performance, GC tuning, thread management, and memory footprint. • Build automation and guardrails for developer productivity and service reliability (CI/CD pipelines, code linting, config-as-code, etc.). • Partner with architecture and leadership to drive long-term technical strategy and platform evolution.

• Design and deliver production features across both frontend and backend • Develop UI components for the operator dashboard (Next.js, React, TypeScript) • Design and implement APIs and backend logic (Bun/Elysia, PostgreSQL) • Integrate external enterprise APIs and internal AI services • Write and maintain tests for critical flows • Own the evolution of key product components, including the approval queue • Develop and improve SLA tracking, escalation logic, and operator workflows • Create analytics views for call trends, approvals, and performance metrics • Support production operations during the enterprise pilot • Monitor, diagnose, and resolve issues in a real-time AI system • Respond to feedback from operators and stakeholders • Improve system reliability, observability, and performance • Work closely with senior engineers on architecture and technical decisions • Participate in code reviews (give and receive feedback) • Document systems and features to ensure long-term maintainability

• Identify emerging AI technologies and build Proofs of Concept (PoCs) • Test bold ideas and prove their value with data • Make high-stakes technical decisions and guide the team through ambiguity • Continuously challenge the current tech stack to ensure it fosters innovation • Partner with C-level and Product leadership to shape company strategy • Influence engineering organization to adopt new standards and technologies • Mentor Senior engineers on technical uncertainty and architectural choices