Senior AI Engineer - End-to-End Document Intelligence (Remote)

Zim Directory; New Jersey; Remote; USD 180,000 - 240,000; Full time

Job summary

Vertican, a long‑standing software company for law firms, is hiring a senior ML engineer to own end‑to‑end document processing pipelines. You will design, benchmark, and experiment with architectures, tools, and thresholds for production readiness.

You will build tooling, work closely with the founding engineering team, and participate in design, planning, and architectural decisions as the first dedicated ML hire on the product.

Qualifications

• 6+ years building ML or data-intensive systems, with 3+ years owning a production pipeline.
• Strong backend engineering and cloud architecture understanding.
• Hands-on experience with document understanding: OCR or layout models.
• Experience with entity resolution at scale against large databases.
• Designed an evaluation from scratch with a labeled ground-truth set and metrics.
• Production experience with LLM APIs, including structured output and tool calls.
• Strong Python and SQL; comfortable with Postgres queries.

Responsibilities

• Design and own end-to-end extraction-to-posting pipelines: classification, extraction, matching, gating, and hand-off to humans.
• Evaluate new systems and run structured trials of components.
• Build evaluation processes for FP/FN/omissions and upgrade decisions.
• Ship components to production in Python, monitor costs and quota, diagnose reviewer cases.

Skills

ML pipelines

Backend engineering

Cloud architecture

Document understanding

Entity resolution

LLM APIs

Python

SQL

Postgres

Tools

Splink

Dedupe

Zingg

Job description

Vertican, a long‑standing software company for law firms, is hiring a senior ML engineer to own end‑to‑end document processing pipelines. You will design, benchmark, and experiment with architectures, tools, and thresholds for production readiness.

You will build tooling, work closely with the founding engineering team, and participate in design, planning, and architectural decisions as the first dedicated ML hire on the product.