Senior Backend Software Engineer, Case Intelligence

Expert Institute • New York, NY

1d

About The Position

Expert Institute is hiring a Senior Software Engineer for its Case Intelligence team, which builds Radar and MRR to transform court records, expert reports, depositions, and medical records into useful information for attorneys. This backend and data engineering role has a strong applied AI component. The engineer will build document-processing pipelines, retrieval systems, and production LLM workflows at scale, with careful attention to output quality, reliability, privacy, and cost.

The role works directly with Product, the evaluation team, and engineering leadership. The engineer is expected to take ambiguous problems from investigation through deployment and production support, own complex projects from technical design through production operation, identify failure modes, make practical tradeoffs, improve quality, communicate risks early, and contribute to technical direction. Success includes reliable and recoverable document processing, measurable quality improvements, lower processing cost and latency as volume grows, secure and observable production systems, and clear communication with product and business partners about capabilities and limitations.

Requirements

• At least five years of professional software engineering experience, including substantial work on backend systems or data pipelines.
• Strong Python skills, including typing, Pydantic, and automated testing, plus solid SQL.
• Production experience with AWS serverless or container services and event-driven systems.
• Experience building with LLM APIs beyond prototypes, with attention to output quality, latency, and cost.
• Experience processing PDFs, scans, OCR output, or other unstructured documents at scale.
• Ability to investigate ambiguous problems, make sound technical decisions, and move work forward independently.
• Clear written communication with technical and nontechnical partners.

Nice To Haves

• Experience with Amazon Bedrock, RAG, vector search, reranking, or LLM evaluation tools such as Langfuse, pydantic-evals, or Label Studio.
• Classic ML or NLP experience in production, including classifiers, embeddings, or entity resolution.
• Experience with OpenSearch/Elasticsearch, Logstash, or Salesforce data integration.
• Experience with infrastructure as code, GitHub Actions, Datadog, and CloudWatch.
• Experience with dbt, Athena, or Looker.
• Experience with TypeScript, NestJS, GraphQL, or Angular.
• Experience in HIPAA or other regulated data environments.
• Experience in legal technology or healthcare.
• Productive use of AI coding agents such as Claude Code or Codex.

Responsibilities

• Design, build, and operate event-driven pipelines using AWS services such as SQS, Lambda, ECS/Fargate, Step Functions, S3, and EventBridge.
• Transform large volumes of unstructured documents into reliable, structured data.
• Build production LLM workflows using Amazon Bedrock, OpenAI, and Gemini, including batch inference, structured outputs, model routing, and long-document processing.
• Develop retrieval and machine-learning components using embeddings, OpenSearch, reranking, classifiers, and entity resolution where they improve results.
• Work with the evaluation team to turn QA findings into measurable improvements in output quality.
• Model and maintain data in PostgreSQL, DynamoDB, OpenSearch, and S3/Athena.
• Make pipelines resilient to bad inputs and unreliable upstream systems through retries, dead-letter queues, idempotency, and backfills.
• Own infrastructure, deployment, access controls, and observability for the systems built.
• Reduce processing time and cost without compromising quality.
• Handle sensitive medical and legal information responsibly and keep technical documentation current.
• Communicate risks early and help other engineers make better technical decisions.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed