Senior Staff Software Engineer, LLM Pipelines

Openkrill; United States; Remote; USD 160,000 - 220,000; Full time

Job summary

Pattern Data is an AI-powered platform designed for the complexities of mass tort litigation. We help leading law firms automate case analysis, accelerate settlements, and manage high-volume inventories with precision.

We’re a collaborative team seeking an engineer to build and operate LLM-backed pipelines, improve accuracy, and own production details like prompts, outputs, and latency. You’ll work with litigation teams to maximize AI value and ship reliable systems.

Qualifications

• Bachelor's degree in CS or related field, or equivalent practical experience.
• 6+ years of software engineering experience with strong fundamentals.
• Hands-on production experience with LLM APIs, prompting and structured outputs.
• Experience with evaluating systems and knowing when to iterate.
• Comfort with messy real-world data (OCR’d PDFs, scanned forms).

Responsibilities

• Build and operate LLM-backed pipelines for document extraction, classification, and validation.
• Measure and improve accuracy using evaluation datasets and metrics.
• Create review workflows for AI outputs validation and correction.
• Own production details: prompts, versioning, validation, cost and latency management.
• Collaborate with litigation team to maximize AI value.

Skills

Software engineering fundamentals

LLM APIs experience

Data handling OCR data

Communication with stakeholders

Problem solving

Education

Bachelor's degree in Computer Science or related technical discipline

Tools

Scala

TypeScript

PostgreSQL

GraphQL

Elasticsearch

AWS

Job description

Pattern Data is an AI-powered platform designed for the complexities of mass tort litigation. We help leading law firms automate case analysis, accelerate settlements, and manage high-volume inventories with precision.

We’re a collaborative team seeking an engineer to build and operate LLM-backed pipelines, improve accuracy, and own production details like prompts, outputs, and latency. You’ll work with litigation teams to maximize AI value and ship reliable systems.