Salary
💰 $100,000 - $120,000 per year
Job Level
Junior
Tech Stack
Google Cloud PlatformOpen SourcePythonSQL
About the role
- Design and build AI pipelines using frameworks like LangGraph, CrewAI, n8n, and LangChain to create modular, testable, and composable agents.
- Build and scale RAG, Graph-RAG, and custom fine-tuned LLM solutions for real estate data normalization, enrichment, summarization, and analytics.
- Develop agent patterns that can reason over tools, retrieve context, and persist goals—bringing multi-step reasoning and tool execution logic to life.
- Collaborate with engineers, product managers, and domain experts to turn exploratory POCs into robust production systems.
- Contribute to internal frameworks and standards for evaluating and debugging agents (e.g., using LangFuse, OpenTelemetry, or custom traces).
- Drive continuous experimentation with memory systems, vector search, and knowledge graph integration for dynamic personalization and logic-based chaining.
- Participate in agent simulation testing and contribute to establishing MCP (Modular Control Plan)-based design strategies for safe and reusable AI behaviors.
Requirements
- 1–3 years experience in applied ML or LLM research or engineering.
- Demonstrated experience building agentic systems using tools like LangGraph, CrewAI, n8n, flowise, or LangChain.
- Deep familiarity with RAG, Graph-RAG, vector stores, and dynamic tool use orchestration.
- Strong Python proficiency.
- Experience with GCP, SQL, and DBT.
- Foundation in statistics, including hypothesis testing, regression, and time series analysis.
- Demonstrated experience applying NLP and transformer-based models in production workflows.
- Real-world use of LangFuse or equivalent frameworks for tracing and observability (preferred).
- Prior work in real estate, financial services, or other structured yet messy domains (preferred).
- Contributions to open source agent or orchestration libraries (preferred).
- Previous experience in developing and deploying LLM-based solutions (preferred).
- Exposure to real estate data or a related field (preferred).
- Strong analytical and problem-solving skills.