This is a remote position.

Senior Full-Stack Engineer – Legal AI / RAG Platform

Company: TeamFicient
Location: Remote

Employment Type: Project-Based
Salary Range: TBD
Work Schedule:

• Time Range: Between 7 AM and 7 PM CST
  

• Working Hours: 9 hours per day (8 working hours + 1-hour break)
  

• Days Off: TBD (2 days per week)
  

Why Join Us?

• Work Without Borders: Collaborate daily with experts from around the world and gain international exposure.
  

• Built for Remote: Join a fully remote culture designed for autonomy, flexibility, and trust.
  

• Diverse Perspectives: Be part of a multicultural team where different backgrounds are our greatest strength.
  

• Grow Globally: Expand your career on a global stage, learning how business works across different cultures and continents.
  

About the Role

We're building a citation-first legal AI platform focused on document intelligence, vector search, and retrieval-augmented generation (RAG). We need a senior, backend-oriented full-stack engineer who has shipped production RAG systems and can design secure, multi-tenant SaaS platforms in compliance-heavy environments.

The MVP is clearly scoped and built on managed cloud services. We value clean architecture, correctness, security, and maintainability, and we actively avoid unnecessary overengineering.

Core Responsibilities

Multi-Tenant Architecture & Security

• Design and build a secure multi-tenant SaaS architecture with strict tenant isolation and access control
  

• Integrate managed cloud services (AWS, GCP, or Azure) to support scalable, reliable infrastructure
  

• Ensure compliance-ready design across all layers of the platform
  

Document Ingestion & Processing

• Develop async ingestion pipelines for PDFs, Word documents, emails, and spreadsheets
  

• Implement document chunking and embedding generation workflows
  

• Integrate read-only connectors with e-discovery platforms, RelativityOne, and DISCO
  

Vector Search & Retrieval

• Build vector search capabilities with metadata filtering for precise document retrieval
  

• Maintain clean separation between ingestion, retrieval, and generation layers
  

• Optimize retrieval accuracy across large legal document sets
  

RAG & Citation Enforcement

• Implement retrieval-augmented generation with strict citation traceability back to source documents
  

• Ensure every AI-generated output is auditable and grounded in cited material
  

Document Viewer & Deep Linking

• Develop an in-app document viewer with deep linking directly to cited source locations
  

Code Quality

• Write production-quality, well-tested, and maintainable code throughout
  

• Participate in architecture decisions and advocate for pragmatic, correct solutions
  

Candidate Qualifications

Must-Haves

• 6–8 years of overall software engineering experience with a strong backend focus
  

• 2–3 years of hands-on experience building and shipping production RAG systems—not just prototypes—including document ingestion pipelines (PDF, Word, email, or similar)
  

• 5+ years of experience with backend development and distributed systems
  

• 3–5 years of experience designing secure multi-tenant SaaS with proper tenant isolation and access control
  

• 3–5 years of experience with managed cloud services—AWS, GCP, or Azure
  

• Proficiency with relational databases and vector search systems (e.g., pgvector, Pinecone, Weaviate)
  

• Background in legal tech, fintech, healthcare, or other compliance-heavy environments
  

Good to Haves

• Familiarity with e-discovery platforms—RelativityOne, DISCO, or similar
  

• Experience with legal technology, AI-driven document analysis, or knowledge graph tools
  

• Exposure to embedding models, LLM APIs, and prompt engineering best practices