Unstructured

Unstructured

Unstructured transforms natural language data for AI by providing open source tools for easy preprocessing and connection to large language models.

IT Services
1-10
Founded 2022
$25M raised

Description

  • Design and implement production-grade RAG pipelines and agentic workflows in Python.
  • Build systems for unstructured and multimodal data, including PDFs, scanned documents, images, and full motion video.
  • Own the lifecycle of AI solutions from initial research through AWS deployment.
  • Evaluate and prototype new models, including LLMs, embedding models, and object detection models.
  • Run experiments to validate approaches for SBIR and government deliverables.
  • Document architectures and contribute to technical reports for contract work.
  • Participate in pre-sales calls to help architect solutions for complex client needs.
  • Translate high-level government requirements into technical roadmaps.
  • Deploy, fine-tune, and optimize open-source models in restricted or air-gapped environments.
  • Work on scalable, performant systems where latency, cost, and accuracy are treated as first-class concerns.

Requirements

  • Proven experience deploying production RAG pipelines on real-world, messy datasets.
  • Deep expertise in agentic system design, including tool use and multi-agent orchestration.
  • Strong Python engineering skills with clean, scalable, maintainable code.
  • Experience operating in AWS and GovCloud environments.
  • Ability to work in restricted or air-gapped environments.
  • Experience deploying, fine-tuning, and optimizing open-source models when commercial APIs are unavailable.
  • Comfort translating high-level government requirements into technical roadmaps.
  • Familiarity with LangChain, LangGraph, CrewAI, or similar orchestration frameworks.
  • Experience fine-tuning NLP or object detection models is preferred.
  • Familiarity with LLM evaluation frameworks such as hallucination detection and drift monitoring is preferred.
  • Knowledge of government security standards and work across classification environments and on-prem environments is preferred.
  • Existing Secret or TS clearance, or clearance eligibility, is a significant plus.
  • Expert-level Python and SQL skills.
  • Experience with vector databases, graph databases, Elasticsearch, BM25, sentence transformers, and related RAG components.
  • Experience with AWS services such as SageMaker, Bedrock, S3, Lambda, Docker, and FastAPI.

Benefits

  • Competitive compensation package.
  • Stock options.
  • Remote full-time work arrangement.
  • Opportunity to work on cutting-edge machine learning projects.
  • Collaborative and innovative work environment.
  • Focus on learning and growth.
  • Opportunity to shape the company’s direction.
  • Impactful work on unstructured data processing for public sector clients.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Staff AI Engineer - US

Typeform 251-1K Internet Software & Services

Typeform is hiring a Staff AI Engineer to shape and operate the AI systems powering Research Flow and other customer-facing products, from experimentation through scalable production delivery.

Apache Airflow Apache Spark AWS CI/CD Datadog Docker FastAPI Generative AI Kafka Kubernetes LLM Machine Learning Microservices MLflow OpenSearch Python PyTorch REST API SageMaker Snowflake SQL Terraform
12 hours, 44 minutes ago

Staff AI Engineer - EU

Typeform 251-1K Internet Software & Services

Typeform is hiring a Staff AI Engineer to shape and operate the AI systems powering Research Flow, turning research concepts into secure, scalable, and dependable customer experiences.

Apache Airflow Apache Spark AWS CI/CD Datadog Docker FastAPI Generative AI Kafka Kubernetes LLM Machine Learning MLflow OpenSearch Python PyTorch SageMaker Snowflake SQL Terraform
13 hours, 29 minutes ago

Senior AI Software Engineer

Caseware 251-1K Internet Software & Services

Caseware is hiring a fully remote AI Platform Architect in Colombia to define, build, and operate scalable, secure, and trustworthy AI capabilities for its global accounting and audit software platform.

AWS AWS CDK Confluence DynamoDB GitHub GitHub Actions JIRA Microservices NestJS Python Terraform TypeScript
1 day, 13 hours ago

AI Ops Engineer GTM

Agiloft 51-250 Capital Markets

Agiloft is hiring an AI Ops Engineer, GTM to shape and deliver practical AI solutions across Sales, Marketing, Customer Success, and Revenue Operations, using customer and market insight to improve productivity, revenue outcomes, and customer experience.

CRM HubSpot Python Salesforce Snowflake
1 day, 13 hours ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers