• Own the overall architecture for AI and ML systems, including data ingestion, preprocessing, feature engineering, training, evaluation, and deployment • Define long-term technical strategy for text and voice analysis, ML pipelines, and model lifecycle management • Make build-vs-buy decisions and select core technologies, frameworks, and cloud infrastructure • Lead the design and implementation of end-to-end ML pipelines from scratch (0 → 1), evolving them into scalable platforms • Ensure pipelines support continuous training, evaluation, deployment, and rollback • Define standards for data versioning, feature stores, model registries, and reproducibility • Oversee data storage, ETL workflows, batch and streaming systems • Ensure strong data quality, labeling strategies, lineage, and versioning practices • Drive best practices for production ML: monitoring, drift detection, performance tracking, and retraining strategies • Ensure AI systems are fault-tolerant, observable, and scalable under production workloads • Build, mentor, and lead high-performing AI, ML, and data engineering teams

• Lead all ML/AI engineering efforts as the first dedicated member of this domain. • Design, build, and ship ML/AI-powered features across multiple products. • Partner closely with Product, Engineering, and Operations to identify high-value opportunities and convert them into production systems. • Own the full lifecycle of ML solutions: problem framing, prototyping, modeling, deployment, monitoring, and continuous improvement. • Establish best practices, tooling, and standards for ML/AI development, experimentation, and observability. • Build and improve data pipelines and feature stores to support robust ML workloads. • Collaborate in architecture reviews, roadmapping, and cross-team planning. • Mentor other engineers on ML/AI concepts and help grow the ML/AI team as the practice scales. • Contribute to a high-quality codebase using TDD, code review, and well-structured engineering practices.

• Build and orchestrate LLM agents using Gemini Pro and LangChain • Design, implement, and operate RAG solutions at scale • Integrate with Gemini and Vertex AI services using API-driven architectures • Debug and optimize end-to-end LLM pipelines, including: chunking strategies, embeddings, retrieval logic, LLM response behavior • Deliver production-ready AI services, including monitoring, rate limiting, and reliability controls • Participate in solution design and technical decision-making • Continuously evaluate and experiment with new LLM models and features as they become available • Implement AI safety, security, and compliance controls across the AI lifecycle • Collaborate with cross-functional teams across time zones

• Build multi-step, tool-using agents that plan, retrieve, act, and verify. • Design agent architectures, integrate tools/APIs, and deliver robust execution with safety and observability. • Architect agent loops (planning, memory, retrieval, tool use, self-verification). • Implement tools (functions/APIs/DB queries/files) and MCP-style interfaces. • Combine RAG with agents: chunking, embeddings, retrieval, reranking, grounding. • Add guardrails: execution sandboxes, permissions, rate limits, PII policies. • Build evaluation for agents (task success, autonomy depth, recovery rate). • Optimize for reliability, determinism where needed, and cost.