Primary Responsibilities 

1. Technical Strategy & Architecture 

• Own the end-to-end architecture for AI products and platforms: 

• Model selection strategy (Google vs. OpenAI, small vs. large models) 

• Multi-agent and workflow orchestration patterns (responder/thinker pattern, tool calling, agentic frameworks) 

• Data and retrieval architecture (RAG, hybrid search, knowledge graphs, semantic caching) 

• Evaluate and introduce emerging technologies such as: 

• Next-generation LLMs and multimodal models 

• Real-time streaming infrastructures 

• Advanced agent frameworks, workflow engines (e.g., Agents SDK, Google ADK,  LangGraph, etc.) 

2. Platformization & Reusable Capabilities 

• Design and lead the implementation of shared AI services and SDKs: 

• Reusable RAG pipelines and ingestion frameworks 

• Common UI components and design patterns for AI copilots and agents 

• Modular reusable coding practices for agentic back-end processes 

• Establish standards and best practices for: 

• Prompt design and versioning 

• Model and retrieval evaluation 

• Observability, logging, and incident response for AI systems. 

3. Leadership & Mentoring 

• Provide hands-on technical leadership to AI Engineers, ML Engineers, and Data Scientists: 

• Guide architectural decisions and code quality 

• Conduct thorough design and code reviews 

• Mentor team members in LLMs, RAG, agentic design, and production AI practices 

• Help define and grow the AI engineering culture, focusing on innovation, quality, and responsible AI. 

4. Delivery & Stakeholder Management 

• Partner closely with Product, Design, and Business stakeholders to: 

• Identify high-value AI use cases aligned with company strategy and PropTech domain needs 

• Shape product roadmaps and define measurable success criteria for AI initiatives 

• Lead complex, cross-functional AI projects from concept to production, ensuring: 

• Clear requirement definitions and project plans 

• On-time delivery with high quality and reliability 

• Ongoing iteration based on user feedback and metrics. 

5. Evaluation, Governance & Responsible AI 

• Define robust evaluation frameworks: 

• Offline and online metrics for relevance, safety, user satisfaction, and business impact 

• Human evaluation workflows for complex or sensitive tasks 

• Drive AI governance and responsible AI practices: 

• Content safety, bias and fairness considerations, PII handling 

• Compliance with internal policies and external regulations (e.g., GDPR-like requirements, data residency) 

• Collaborate with security, privacy, and legal teams to ensure compliant AI solutions. 

6. Performance, Reliability & Cost Management 

• Lead performance and cost optimization for AI systems: 

• Model routing, distillation, and caching strategies 

• Right-sizing infrastructure and making build-vs-buy decisions 

• SLAs/SLOs for key AI services, including latency, uptime, and error budgets. 

• Proactively identify and mitigate technical risks related to scalability, data quality, or vendor lock-in. 

Required Knowledge / Skills / Abilities 

• Typically 8+ years of experience in Software Engineering, ML Engineering, or Data Science, with 3+ years hands-on in Applied AI/LLMs and at least 2+ years in a senior/lead role. 

• Deep expertise in: 

• Python and TypeScript/JavaScript in production environments 

• Designing and operating distributed, cloud-native systems (GCP, Azure, or AWS) 

• Containerization and orchestration (Docker, Kubernetes) and modern CI/CD. 

• Working with coding assistants like Windsurf, Cursor, Codex, etc. 

• Proven track record of: 

• Architecting and shipping complex AI systems to production at scale 

• Leading multi-engineer initiatives and mentoring others 

• Making data-driven tradeoffs between speed, quality, and cost. 

• Advanced experience with: 

• LLM-based application design (prompting, tool use, function calling, multi-agent workflows) 

• RAG architectures, vector databases, and retrieval optimization techniques 

• AI observability, monitoring, and evaluation frameworks. 

• Excellent communication and stakeholder management skills: 

• Ability to communicate complex AI concepts to executives and non-technical partners 

• Comfortable representing AI strategy and progress to leadership and cross-functional teams. 

Nice-to-Have Skills / Abilities 

• Experience with: 

• Working with coding assistants like Windsurf, Cursor, Codex, etc.  

• Multimodal and real-time agents (voice + text + UI control, streaming interactions). 

• Background in: 

• AI experiment tracking and evaluation frameworks (e.g., OpenAI Evals, Langsmith Evals, etc.)   

• Data platforms (data lakes/warehouses, feature stores, event streams like Kafka) 

• Browser automation software such as PlayWright  

• Designing AI products in domains with strong regulatory or privacy constraints. 

• Experience building organizational AI strategies, setting standards, and helping define AI hiring and capability roadmaps. #LI-JL1 #LI-REMOTE