Forward-Deployed AI Engineer, Backend

Draftwise; New York (NY); On-site; USD 135,000 - 175,000; Full time

Benefits offered by this job

Meaningful equity

Series A impact

Job summary

Draftwise is seeking an early-career Forward Deployed AI Engineer to embed with a law firm and translate how lawyers draft into an ontology, then build the backend (and enough frontend) to extend the product so it operates the way the firm works. This role blends backend engineering with production AI systems, applied directly in real customer environments, with onsite work at our New York office.

You'll own features end to end, including modeling a firm's precedent, writing tests, and

Qualifications

• Backend-focused role with SQL, API design, and debugging skills.
• Comfort in working closely with customers to gather precise requirements.
• Ability to turn ambiguous problems into models for AI systems.
• Interest in LLMs and understanding their limits.
• High ownership and low ego with strong problem-solving.

Responsibilities

• Model a firm's precedent into an ontology and implement the backend.
• Embed with the firm to learn how lawyers draft, then extend the product until it aligns with their workflows.
• Own features end to end, including understanding how the pieces work together.
• Write and test prompts, build retrieval and evaluation scaffolding.
• Profile, query tuning, and cost-related work for scale and performance.
• Lead early rollout pieces and investigate why a playbook does not map cleanly onto the product.
• Ship UI changes without waiting on others.

Skills

SQL

API design

Debugging services

Customer-facing

Problem modeling

LLMs

Ownership

Tools

Postgres

OpenSearch

Graph database

AWS

TypeScript

React

Claude Code

Job description

Draftwise is seeking an early-career Forward Deployed AI Engineer to embed with a law firm and translate how lawyers draft into an ontology, then build the backend (and enough frontend) to extend the product so it operates the way the firm works. This role blends backend engineering with production AI systems, applied directly in real customer environments.

Location and Compensation

• Location: New York, NY (onsite)
• Salary: USD 135,000 - 175,000 per year

What You Will Do

• Model a firm’s precedent and playbooks into an ontology, and implement the backend that sits behind it; when platform capabilities fall short for a firm’s needs, build the missing parts.
• Embed with the firm to learn how lawyers draft, then extend the product until it aligns with their workflows.
• Own features end to end, including understanding how the pieces work together.
• Write and test prompts, build retrieval and evaluation scaffolding, and measure quality using real customer data.
• Perform profiling, query tuning, and cost-related work as part of routine engineering for scale and performance.
• Lead early pieces of a firm’s rollout and investigate why a playbook does not map cleanly onto the product.
• Ship UI changes without waiting on others.

Core Responsibilities in Practice

You will apply production engineering to LLM-driven systems, including drafting, review, and search workflows. The work includes ontology modeling for legal knowledge, backend services behind product features, and engineering improvements that support scale, performance, and deployments into elite law firms, alongside a senior Forward Deployed Engineer.

Required Qualifications

• Backend as your center of gravity, with comfort in SQL, API design, and debugging services you did not write.
• Comfort working closely with the customer by asking precise questions and clearly stating what information is still needed.
• The instinct to turn an ambiguous problem into a model.
• Interest in LLMs and their limits.
• High ownership and low ego.

Technologies

• Postgres
• OpenSearch
• Graph database
• AWS
• TypeScript
• React
• Microsoft Word
• Claude Code

Benefits

• Meaningful equity package for every engineer, so you own a part of what you build.
• Joining at Series A, with work that continues to shape the company’s trajectory.

Nice to Have

• Project or internship experience involving retrieval systems, evaluation harnesses, or agent frameworks.
• Experience working with customers, including consulting, support, or solutions work.
• Exposure to legal, financial, or other document-heavy domains.
• Anything shipped to real users, including personal projects.

Interview Process

• Intro call with the hiring manager.
• Technical conversation on a system you have built.
• Screen share coding exercises of about an hour on backend, data modeling, and debugging.
• Take-home project of about 3 hours on a self-contained problem using the company stack and AI tools you would use on the job; the rate and evaluation criteria are shared in advance.
• Final conversation with a founder.