• Building AI-powered internal tools and data-driven systems used across the organization - analytics platforms, reporting automation, workflow intelligence. • Developing AI/ML-driven platforms that process and analyze large-scale operational data from 30M+ sites across our product suite. • Designing and deploying RAG systems, LLM-powered features, and agentic workflows that generate actionable insights for internal teams. • Building data pipelines that ingest, transform, and serve behavioral and operational data at scale. • Prototyping and shipping AI solutions that streamline internal processes, reduce manual effort, and improve decision-making. • Evaluating and selecting the right models, frameworks, and infrastructure for each use case - balancing performance, cost, and latency. • Writing clean, well-tested, production-grade Python code with proper error handling, logging, and observability. • Collaborating with product teams and stakeholders to understand what they need, then building tools they actually use. • Keeping up with the rapidly evolving AI landscape and bringing new ideas, tools, and approaches to the team. • Communicating with the team and supporting your peers using chat, audio, and video.

• Design and build AI-powered features, pipelines, and automation workflows from scratch • Integrate and fine-tune LLMs, embedding models, and other ML systems into production applications • Develop and maintain RAG pipelines, vector search systems, and agent-based architectures • Write clean, well-structured code across backend and API layers to support AI feature delivery • Evaluate, benchmark, and iterate on model outputs to ensure quality and reliability • Collaborate with cross-functional teams to scope requirements and architect AI solutions • Stay current with the rapidly evolving AI landscape and proactively introduce relevant tooling and approaches • Document technical designs, system behaviour, and deployment processes clearly and thoroughly

• Design, build, and operate multi-agent workflows and tool-enabled agents • Architect and maintain end-to-end RAG systems • Evaluate and integrate LLMs and GenAI services • Develop and optimize prompting strategies • Define and own evaluation frameworks for generative outputs • Build scalable, secure AI infrastructure on AWS • Own the full deployment lifecycle for models and agents • Ensure data quality through rigorous validation and augmentation

• Develop ML models and supporting services for classification, clustering, similarity search, and prediction. • Implement RAG pipelines: document ingestion, embedding generation, vector indexing, and retrieval tuning. • Build APIs and microservices to expose model capabilities to enterprise systems. • Integrate ML components into existing DevSecOps pipelines (Azure DevOps, CI/CD workflows). • Implement duplicate detection, ticket routing, SLA prediction, and root-cause assist features. • Optimize model performance for latency, throughput, and accuracy. • Conduct model evaluation, error analysis, and iterative tuning. • Work with Data Engineer to align data pipelines with model input requirements. • Ensure outputs are explainable, auditable, and compliant with governance controls.