Data Architect

Job Description:

 

Anywhere is at the forefront of driving the digital transformation and building best-in-class products that help our agents and brokers sell more homes, make more money, and work more efficiently.

Data & Analytics (DNA) is Any where’s data arm. We create innovative analytics, data science, and robust data foundation capabilities to generate data-driven insights that serve the heart of Anywhere Advisor and Anywhere Brand business. Together with our business counterparts in the real estate business, we work daily to deliver differentiating insights (AI & BI) for Strategy and AA & AB Operations.

We are seeking a Data Platform Engineer with expertise in building Agentic AI systems—where autonomous agents collaborate, make decisions, and act in real time using structured and unstructured data. In this role, you will design, implement, and maintain a data platform that powers intelligent agents with high-performance data ingestion, contextual memory, observability, and LLM integration.

Key Responsibilities
• Design and implement scalable data ingestion and transformation pipelines (real-time and batch) to support autonomous AI agents. This includes data from third-party APIs, ServiceNow, Google GA4, JIRA, Zendesk, and other complex systems.
• Collaborate on developing Data Quality and Ops Platforms for real-time data anomaly detection and data profiling.
• Develop and maintain agent memory architecture (vector stores, knowledge graphs, temporal data stores).
• Integrate LLMs (e.g., OpenAI, Claude, Gemini) and agent frameworks (LangChain, AutoGen, CrewAI, MetaGPT).
• Build and manage APIs, event buses, or pub/sub systems that enable agent-to-agent communication and coordination.
• Optimize platform performance, including data indexing, latency reduction, and load balancing for multi-agent orchestration.
• Develop tools and dashboards for platform observability, including agent metrics, prompt lifecycle tracking, and model drift.
• Implement security, data governance, and versioning practices in agent workflows and interactions.
• Collaborate with AI research, backend, and product teams to ship features powered by multi-modal, memory-augmented agents.
• Develop CI/CD processes for continuous delivery in AWS and Snowflake Cloud.
• Support and Troubleshoot: Perform production troubleshooting and resolution, focusing on observability to detect issues in advance.

Skills and Qualifications
• 3+ years of experience in data engineering, ML platforms, or backend systems.
• Strong experience with Python, SQL, and modern data frameworks (e.g., Apache Spark, Airflow, dbt, Kafka).
• Familiarity with LLM-based agent frameworks (e.g., LangChain, LlamaIndex, AutoGen, CrewAI).
• Experience with vector databases (e.g., Pinecone, Weaviate, FAISS) and semantic search.
• Experience building event-driven architectures (Kafka, Pub/Sub, or similar).
• Understanding of LLM orchestration, prompt engineering, and tool-use paradigms.
• Experience working with cloud platforms (AWS, GCP, or Azure).
• Communication Skills: Excellent written and verbal communication skills in English.
• Problem Solving Skills: Strong analytical & problem-solving skills to identify data issues and performance bottlenecks.

Preferred Qualifications
• Prior work in multi-agent systems or agent-based simulations.
• Experience with data-centric AI pipelines, RAG (retrieval-augmented generation), or knowledge graphs.
• Familiarity with LangGraph, DSPy, or other agent state management tools.
• Exposure to observability tools (e.g., DataDog, Prometheus, Grafana, OpenTelemetry).
• Open-source contributions in agent ecosystems or AI infrastructure