We are seeking a versatile Data Engineer with 4-7 years of experience to own end-to-end data pipelines for downstream AI agent applications. You’ll design data models and transformations, build scalable ETL/ELT workflows, and collaborate on ML model deployment, while learning fast and working on the AI agent space. Key Responsibilities Data Modeling & Pipeline development Define and implement logical/physical data models and schemas Develop schema mapping and data dictionary artifacts for cross-system consistency Build, test, and maintain robust ETL/ELT workflows using Spark (batch & streaming) Automate data ingestion from diverse sources (Databases, APIs, files, Sharepoint/document management tools, URLs) Gen AI Integration Collaborate with AI engineers to enrich data for agentic workflows Instrument pipelines to surface real-time context into LLM prompts ML Model Deployment Support (Secondary role) Package and deploy ML models (e.g., via MLflow, Docker, or Kubernetes) Integrate inference endpoints into data pipelines for feature serving Observability & Governance Implement monitoring, alerting, and logging (data quality, latency, errors) Apply access controls and data privacy safeguards (e.g., Unity Catalog, IAM) CI/CD & Automation Develop automated testing, versioning, and deployment (Azure DevOps, GitHub Actions, Airflow) Maintain reproducible environments with infrastructure as code (Terraform, ARM templates) Required Skills & Experience 5 years in Data Engineering or similar role, with exposure to ML modeling pipelines Proficiency in Python , dlt for ETL/ELT pipeline, duckDB for analytical in-process analysis, dvc for managing large files efficiently. Solid SQL skills and experience designing and scaling relational databases. Familiarity with non-relational column based databases. Familiarity with Prefect is preferred or others (e.g. Azure Data Factory) Proficiency with the Azure ecosystem. Should have worked on Azure services in production. Familiarity with RAG indexing, chunking and storage across file types for efficient retrieval. Experience deploying ML artifacts using MLflow, Docker, or Kubernetes Strong Dev Ops/Git workflows and CI/CD (CircleCI and Azure DevOps) Bonus skillsets: Prompt Engineering Agent Workflows Experience with Machine Learning and/or Computer Vision Knowledge of data-governance (GDPR, CCPA) and enterprise security patterns Obs: We are an early-stage startup, so you are expected to wear many hats, working with things out of your comfort zone, but with real and direct impact in production. If you think you are a good fit for this fast-paced environment, please apply - no direct messages, e-mails will be considered. Why us? Fast-growing, revenue-generating proptech startup Steep learning opportunities in real world enterprise production use-cases Remote work with quarterly meet-ups Multi-market client exposure
Drive the design, build, deployment, and continuous improvement of agentic AI applications for the real estate and construction industry. You’ll own end-to-end agent frameworks, architecting tool chains, crafting prompts, integrating data, and running observability and feedback loops to deliver production-grade AI agents. Key responsibilities: Agent Architecture & Orchestration Design and implement agent pipelines using frameworks like LangGraph, Google ADK, CrewAI, etc. Wire up external APIs, custom tool calls and endpoint integrations Prompt Engineering & Feedback loops Develop, iterate, and optimize domain-specific prompt templates at speed Embed complex business logic into multi-step prompt workflows Build user-feedback pipelines to retrain, fine-tune, and adjust agent behavior Secure Deployments Containerize and deploy LLMs securely on Azure Cloud (AKS /Azure ML). Familiarity with secure LLM application deployments in Kubernetes clusters. Manage CI/CD for model updates and environment provisioning (Terraform) Observability & Evals Build monitoring and logging for agent performance, latency, failures and error handling. Implement agent eval frameworks and track metrics over time (RAGAS, DeepEval/ Langfuse, etc.) Collaboration Partner with backend & data engineers to deliver end-to-end product Document architectures, runbooks and learnings from iterations Required skills and experience: 4–7 years in data science (ML engineering/computer vision), with over 12 months of LLM production experience Hands-on with agentic AI frameworks; strong preference for LangGraph Expert prompt and context engineering skills in complex, domain-specific contexts Proven track record deploying models in secure cloud environments. Working experience in the Azure ecosystem is essential. Experience with containerization (Docker, Kubernetes) and serverless compute Familiarity with observability & eval platforms (Langfuse/LangSmith) Ability to translate nuanced business logic into detailed agent workflows and prompts. Strong coding skills in Python, plus experience with REST/gRPC API integrations Nice to have skillsets: Fine-tuning open source models (DeepSeek/Llama/Mistral) for narrow domain based tasks, ensuring higher overall accuracy & consistency Prototyping RL-based improvements or RL-as-a-Service experiments Prior production exposure to real estate, construction or manufacturing domains in building and deploying any data science application (not necessarily LLM based) We are an early-stage startup, so you are expected to wear many hats, working with things out of your comfort zone, but with real and direct impact in production. If you think you are a good fit for this fast-paced environment, please apply on the form. No direct messages, e-mails will be considered please. Why us? Fast-growing, revenue-generating startup Multi-market client exposure Non-hierarchical environment. Build together, ship together, grow together. Steep learning opportunities in real world enterprise production use-cases Remote work with quarterly meet-ups