Senior Backend & LLM Data Engineer

Expert Institute; New York (NY); On-site; USD 150,000 - 190,000; Full time

Job summary

Expert Institute is hiring a Senior Software Engineer to join our Case Intelligence team. You will build document-processing pipelines, retrieval systems, and production-ready LLM workflows that scale, handling court records, expert reports, depositions, and medical data with attention to privacy, reliability, and cost.

You will collaborate with Product, evaluation, and engineering leadership to take ambiguous problems from investigation through deployment and production support, delivering

Qualifications

• At least 5 years of professional software engineering experience including backend systems or data pipelines.
• Strong Python skills with typing, Pydantic, and automated testing; solid SQL.
• Production experience with AWS serverless or container services and event-driven systems.
• Experience building with LLM APIs beyond prototypes, focusing on output quality, latency, and cost.
• Experience processing PDFs, scans, OCR output, or other unstructured documents at scale.
• Clear written communication with technical and nontechnical partners.

Responsibilities

• Design, build, and operate pipelines using AWS services such as SQS, Lambda, ECS/Fargate, Step Functions, S3, and EventBridge.
• Turn large volumes of unstructured documents into reliable, structured data.
• Build production LLM workflows with Bedrock, OpenAI, and Gemini, including batch inference and long-document processing.
• Develop retrieval and ML components using embeddings, OpenSearch, reranking, and entity resolution.
• Collaborate with evaluation team to translate QA findings into measurable quality improvements.
• Maintain data in PostgreSQL, DynamoDB, OpenSearch, and S3/Athena.

Skills

Python

SQL

AWS

Backend systems

LLM APIs

PDF processing

Tools

AWS

OpenAI

Bedrock

OpenSearch

Pydantic

Job description

Expert Institute is hiring a Senior Software Engineer to join our Case Intelligence team. You will build document-processing pipelines, retrieval systems, and production-ready LLM workflows that scale, handling court records, expert reports, depositions, and medical data with attention to privacy, reliability, and cost.

You will collaborate with Product, evaluation, and engineering leadership to take ambiguous problems from investigation through deployment and production support, delivering