Agentic AI Engineer

Position : Agentic AI Engineer – Real Estate & Construction

Job Type : Full-time

Location : Remote (Quarterly Meet-ups)

About the Role :

We are seeking a talented engineer to drive the design, deployment, and continuous improvement of agentic AI applications in real estate and construction. You will own the full lifecycle of agent frameworks, including toolchain architecture, prompt engineering, data integration, and observability, ensuring production-grade AI agents.

Key Responsibilities :

Agent Architecture & Orchestration :

Design and implement agent pipelines using frameworks like LangGraph, Google ADK, CrewAI, etc.

Integrate external APIs, custom tool calls, and endpoints.

Prompt Engineering & Feedback Loops :

Develop and optimize domain-specific prompt templates.

Embed complex business logic into multi-step 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).

Manage CI / CD pipelines and environment provisioning (Terraform).

Observability & Evaluations :

Monitor agent performance, latency, failures, and error handling.

Implement agent evaluation frameworks (RAGAS, DeepEval, Langfuse) and track metrics over time.

Collaboration :

Work closely with backend and data engineers to deliver end-to-end solutions.

Document architectures, runbooks, and lessons learned from iterations.

Required Skills & Experience :

4–7 years in Data Science / ML Engineering (including computer vision), with 12+ months of LLM production experience.

Hands-on experience with agentic AI frameworks; LangGraph experience preferred.

Strong prompt engineering skills in complex, domain-specific contexts.

Proven experience deploying models securely in cloud environments (Azure preferred).

Familiarity with containerization (Docker, Kubernetes) and serverless computing.

Experience with observability & evaluation platforms (Langfuse, LangSmith).

Strong Python coding skills and experience with REST / gRPC API integrations.

Ability to translate complex business logic into detailed agent workflows.

Preferred / Nice-to-Have :

Fine-tuning open-source models (DeepSeek, Llama, Mistral) for domain-specific tasks.

Prototyping RL-based improvements or RL-as-a-Service experiments.

Prior production exposure to real estate or construction data science applications.

Why Join Us :

Fast-growing, revenue-generating proptech startup.

Real-world enterprise production use cases for steep learning.

Remote-first, with quarterly meet-ups.

Exposure to multiple markets and diverse clients.

Note :

As an early-stage startup, candidates are expected to wear multiple hats, work beyond their comfort zone, and have direct impact in production. Only applications submitted through the official channel will be considered.