Job Description
Job Description
Data Science & AI LLM (Applied GenAI, Cloud & Product Engineering) | Snaphomz
About Snaphomz:
Snaphomz is a US-based real estate startup on a mission to make home buying transparent, tech-enabled, and human-first. We are building an AI-first platform that helps buyers, sellers, and agents make confident decisions across the entire property lifecycle. Our systems combine conversational AI, real estate data, and robust cloud infrastructure to deliver practical outcomes at scale. We don’t just experiment; we build for real users on real production systems.
The Role:
We are looking for a highly motivated AI Intern who is comfortable operating across the full stack—AI, backend, cloud infrastructure, and frontend layers. This role is designed for a builder who wants deep, hands-on exposure to how modern AI products are actually architected, deployed, and monitored in a high-growth startup environment. You will work directly with the founding and engineering teams to bridge the gap between LLM research and production-grade software.
Key Responsibilities:
- Applied AI Development: Build and integrate LLM-powered features like conversational search, decision summaries, and guided workflows. Experiment with prompting strategies, evaluation frameworks, and observability tools.
- Cloud Infrastructure (IaC): Develop and maintain backend services on AWS (Lambda, API Gateway, S3, CloudFront, Route 53). Use AWS CDK to define infrastructure as code.
- DevOps & CI/CD: Manage environments using Docker and YAML configurations. Maintain automated deployment pipelines via GitHub Actions and manage code through rigorous branching and PR strategies.
- Full-Stack Integration: Collaborate with the frontend team to integrate AI outputs into React applications using JavaScript/TypeScript, ensuring features are delivered end-to-end.
- Data Architecture: Explore and implement graph databases to connect structured and unstructured real estate data.
Required Skills & Fundamentals:
- Strong fundamentals in Python and/or JavaScript/TypeScript.
- Expert-level comfort with GitHub (Branching, PRs, Actions).
- Solid understanding of RESTful API design and backend architectural concept
- Familiarity with AWS services and the concept of Infrastructure as Code.
- Ability to read and modify Docker configurations and deployment files.
Preferred "Plus" Skills:
- Experience with Agentic frameworks (LangChain, CrewAI, etc.) or Graph Databases (Neo4j).
- Exposure to LLM observability and debugging tools (LangSmith, Arize, etc.).
- Prior experience with AWS CDK or Terraform.
- A portfolio of deployed projects or an active GitHub presence.
What We’re Looking For:
- You take responsibility for tasks from conception to deployment.
- You can pick up unfamiliar tools (like new AWS services or AI frameworks) in a matter of days.
- You are comfortable with fast-moving timelines and occasional Saturday sprints during critical execution phases.
- You enjoy operating across boundaries rather than staying in a narrow niche.
How to Apply:
Please submit your Resume, GitHub profile, and links to any live deployments or relevant projects. Include a brief note explaining why you are excited to work at the intersection of AI, Cloud, and Product Engineering in a startup environment.