Software Engineer

Expert Institute
New York, United States
2 days ago
Apply on startup.jobs
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Working hours
Regular working hours
Job source

Tech stack

Amazon Web Services Amazon S3 Automation of Tests Law Practice Management Software Customer Data Management Data Deduplication Information Engineering Data Infrastructure Data Integration Amazon DynamoDB Elasticsearch Github
+35 more
Information Retrieval Python (Programming Language) PostgreSQL Named Entity Recognition OpenAI Logstash Search Technologies SQL Databases TypeScript Datadog Retrieval-Augmented Generation Large Language Models Claude Code State Machines AI Coding Agents Backend Langfuse β€” LLM Observability and Analytics Platform Servicebus Event Driven Architecture AngularJS Infrastructure Automation Frameworks Amazon Bedrock Low Latency AWS Fargate Graphql Google Gemini Cloudwatch Entity Resolution NestJS Model Inference Amazon Simple Queue Service (SQS) Looker Analytics Data Pipelines Serverless Computing OpenSearch

Job description

You will work directly with Product, our evaluation team, and engineering leadership. You should be comfortable taking an ambiguous problem from investigation through deployment and production support.

What You’ll Work On

  • Event-driven pipelines behind Radar and MRR
  • PDF parsing, OCR, classification, and entity extraction
  • LLM inference, retrieval, and evaluation
  • Court-record and third-party data integrations
  • Data quality, entity resolution, and deduplication
  • Processing cost, performance, and production reliability

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 using Amazon Bedrock, OpenAI, and Gemini, including batch inference, structured outputs, model routing, and long-document processing.
  • Develop retrieval and ML components using embeddings, OpenSearch, reranking, classifiers, and entity resolution where they improve results.
  • Work with our 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 the infrastructure, deployment, access controls, and observability for the systems you build.
  • Reduce processing time and cost without compromising quality.
  • Handle sensitive medical and legal information responsibly, and keep technical documentation current.

How We Define This Level A Senior Software Engineer owns complex projects from technical design through production operation. You are expected to identify failure modes, make practical tradeoffs, improve quality over time, and communicate risks early. You will contribute to the team’s technical direction and help other engineers make better decisions. Success Looks Like

  • Radar and MRR process documents reliably, with failures visible and recoverable.
  • Output quality improves through measured changes informed by evaluation and QA.
  • Processing costs and latency improve as volume grows.
  • The systems you build are secure, observable, and supportable in production.
  • Product and business partners understand what the systems can do, where they fall short, and what you are improving next.

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.
  • The ability to investigate ambiguous problems, make sound technical decisions, and move work forward independently.
  • Clear written communication with technical and nontechnical partners.

Helpful Experience

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

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on startup.jobs
Prepare application

Good distractions

Loading talks and stories from around this role…