• Own AI features end-to-end, from problem statement to GA • Move features through our rollout tiers (prototype → design partner → beta → GA), earning each promotion with an eval baseline and a capacity plan • Build and defend evals: golden datasets, a north-star metric per feature, and online monitoring — so we can *see and prove* how a feature behaves, not guess • Lead the "meaning" layer of our semantic stack: retrieval semantics, embedding quality (proven first on initiative-candidate retrieval), and the label flywheel that feeds prompt optimization and golden sets. You co-design our vector and knowledge-graph stores with the AI Platform team — you're their most demanding customer • Push output quality with the levers that matter: context assembly, prompt optimization, and per-customer/per-firm generation • Work closely with cross-functional teams — product managers, designers, and other engineers — to gather requirements, define measures of success, and deliver high-quality solutions • We want you not just to build but to *engage* with our product and our users. Your input and opinion will be highly valuable, and it is expected that you have many thoughts on how things should be done and why

• Implement new product features & support/ extend existing ones • Build frontend platform components leveraged across our internal, external products and ecommerce storefronts like Shopify, Salesforce etc • Work with product and design teams toTranslate product and design work (Figma) into robust, accessible, high-performance UI components • Own frontend architecture decisions and uphold code-quality standards alongside other senior engineers, and mentor teammates through code review • Contribute to development and maintenance of backend services using primarily Golang, Node.js • Understanding of google cloud platform (GCP), CI/CD and be able to deploy code and infrastructure components • Work with datastores like PostgreSQL, Cloud Spanner, BigQuery, and Bigtable • Understand and implement RESTful or GraphQL APIs

• Design, develop, and deploy scalable AI and Generative AI solutions. • Build LLM-powered applications, intelligent assistants, copilots, AI agents, and automated workflows. • Design and implement Retrieval-Augmented Generation (RAG) architectures. • Implement semantic search, embeddings, knowledge retrieval, and vector database solutions. • Integrate Large Language Models through Azure OpenAI, OpenAI APIs, or equivalent AI platforms. • Develop prompts, tools, function-calling workflows, and agent orchestration mechanisms. • Evaluate and select AI models, frameworks, and architectures according to each use case. • Define evaluation criteria and monitor the accuracy, quality, latency, security, and cost of AI solutions. • Integrate AI capabilities into existing software products and enterprise applications. • Transform business requirements into scalable, secure, and production-ready technical solutions. • Provide technical leadership and define development standards and best practices for AI initiatives. • Collaborate with multidisciplinary technical and business teams.

• Lead a multidisciplinary squad, fostering a collaborative, autonomous, and results-oriented environment. • Orchestrate the use of AI agents across the entire Software Development Life Cycle (SDLC), ensuring their application in appropriate contexts and adherence to quality and governance standards. • Facilitate Agile ceremonies (Planning, Daily, Review, and Retrospective), adapting the workflow to a development model supported by AI. • Manage the backlog in partnership with Product Managers and stakeholders, prioritizing deliveries that provide the greatest business value. • Continuously monitor the quality of human deliverables and outputs generated by AI agents, refining workflows, prompts, and configurations as needed. • Define and track productivity, quality, efficiency, and AI adoption metrics for the squad. • Remove impediments and manage risks, ensuring predictability in deliveries. • Promote continuous alignment between product, business, and technology, ensuring transparent communication with all stakeholders. • Encourage technical development of the team and continuous improvement of engineering practices and collaboration with AI. • Identify opportunities for continuous improvement, automation, and optimization of the development process.