Senior ML Researcher

Drafted; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Drafted is building foundational models and generative pipelines to create floor plans and renderings in an instant, enabling anyone to imagine a dream home. As an ML researcher, you will contribute meaningfully toward advancing the capabilities for our foundational model and collaborate with both engineering and research teams.

Ideal candidates will have experience with diffusion models, context-aware generation, and reinforcement learning to improve model accuracy.

Qualifications

• Experience iterating on novel techniques to improve diffusion-model KPIs.
• Ability to reproduce and productionize novel methods with/practitioners where needed.

Responsibilities

• Advance capabilities of our foundational ML model across research and engineering teams.
• Collaborate with researchers and engineers to drive experiments and deployments.
• Work on projects like multi-layer context handling, vector-output model integration, and RL-based accuracy improvements.

Skills

Diffusion models

Reinforcement learning

Context-aware generation

Tools

Pytorch

Experimentation tooling

Job description

About Drafted

Drafted is unlocking creativity in the physical world. We’re building foundational models and generative pipelines that create floor plans and renderings instantly, so anyone can imagine their dream home. Starting with single-family homes, we plan to verticalize across all dimensions of the pre‑construction stack.

Generative architecture is a prime domain for applied research with abundant data, verifiable constraints, and a clear value proposition. Our team of second‑time founders, engineers, and designers pairs exceptional product taste with deep technical rigor to turn real‑world buildability constraints into an intuitive, magical experience.

Drafted's Values

• Own the mission. We take agency, act like owners, and see problems through to real outcomes.
• Build in the open. We value direct feedback, fast learning, and growth through honest collaboration.
• Move with care and speed. We iterate quickly while staying deeply respectful of our teammates.
• Seek the why. We challenge assumptions, think from first principles, and never stop asking questions.
• Design for everyone. We believe anyone should be able to design and build a home they love.
• Solve what matters. We embrace hard problems and create new paths forward when none exist.

The Role

As an ML researcher you’ll contribute meaningfully towards advancing the capabilities for our foundational model. You’ll work closely with teammates across both the engineering and research teams.

Example Projects

• Teach our ML model how to handle multiple layers of context and constraints to consider in the generation process (i.e. Structural engineering, Civil engineering, Electrical, etc).
• Figure out how to add direct to vector as an output of the model.
• Use RL to increase the accuracy of the model.

Ideal Experience

• Iterated on novel techniques for meaningfully improving some KPI for diffusion models
• Provided code for reproducing said novel techniques if open sourced, otherwise worked with practitioners for productionizing the techniques