Applied ML Engineer - End-to-End Housing Verification

Two Dots; San Francisco (CA); On-site; USD 350,000 - 400,000; Full time

Job summary

Two Dots, based in San Francisco, builds verification and risk infrastructure to tackle the housing crisis. We are hiring a Machine Learning Engineer for a low-headcount, high-impact role focused on applied ML problems in housing verification, underwriting, fraud detection, and document understanding. You will develop models from scratch end-to-end.

This is not a research role; you will implement evaluation pipelines, drive quality, and create systemic ML improvements across the team.

Qualifications

• Take ambiguous problems and translate them into technical plans.
• Proficient in PyTorch with end-to-end model development and deployment.
• Strong statistical foundation and quality management for ML systems.

Responsibilities

• Develop ML models from scratch for housing verification and underwriting.
• Detect fraud and analyze documents (PDFs, text, images) for authenticity.
• Build evaluation systems and ensure model reliability and governance.
• Improve ML pipelines, prompting workflows, and system performance.
• Collaborate on data workflows and compute efficiency at scale.
• Educate team on best practices for ML evaluation and deployment.
• Contribute to multimodal understanding and risk assessment models.

Skills

PyTorch

Tensor operations

Model deployment

Metrics-driven evaluation

Statistics

Computer vision

NLP

Multimodal understanding

BigQuery SQL

Job description

Two Dots, based in San Francisco, builds verification and risk infrastructure to tackle the housing crisis. We are hiring a Machine Learning Engineer for a low-headcount, high-impact role focused on applied ML problems in housing verification, underwriting, fraud detection, and document understanding. You will develop models from scratch end-to-end.

This is not a research role; you will implement evaluation pipelines, drive quality, and create systemic ML improvements across the team.