Job title: Full-Stack Software Engineer — LLM Tooling & Data Applications

Job type: Contract

Contract Length: Through end of 2026

Rate: $70 – $90 per hour (W2)

Role Location: 100% Remote (United States)

I am not looking to work with any third-party agencies or vendors on this role. Seriously guys, please don't call me. Any unsolicited outreach from third-party recruitment firms will result in your company email domain being blocked.

The company:
One of our long-standing US-based technology clients is growing the engineering team behind their internal planning and reporting platform. The team builds the software their organization uses to track engineering delivery, plan headcount, and keep leadership informed on what's being built and when.

Role and Responsibilities:
You'll be joining a small full-stack team building internal applications that blend traditional data-driven web tooling with newer AI-assisted features — chat interfaces over internal data, retrieval-augmented generation, graph-backed search, and dashboards that pull from a mix of enterprise systems. The exact day-to-day will depend on your strengths, but you'll be working across the backend, data, and LLM tooling layers of a modern internal platform.

Build and ship features across a TypeScript and Node backend with data and AI-assisted components
Work on LLM-powered features including prompt engineering, retrieval-augmented generation, and integration with internal data sources
Contribute to graph-database-backed retrieval and semantic search work
Integrate with enterprise SaaS platforms and internal data systems via their APIs
Partner with frontend engineers on data visualization and dashboard work
Participate in code review, deployment automation, and standard quality engineering practices
Work directly with internal users to scope, prototype, and refine what gets built

Job Requirements:

• 3+ years building production web or data applications with Node.js and TypeScript
• Practical experience with LLM prompt engineering and production retrieval-augmented generation (RAG) pipelines
• Working knowledge of a graph database such as Neo4j or Memgraph, or equivalent experience with semantic search layers over a data warehouse
• Comfort with modern LLM tooling patterns including tool use, agent architectures, and integration with enterprise data sources
• Familiarity with enterprise engineering tooling — ticketing, source control, observability, and deployment pipelines
• Comfortable operating in an agile team with CI/CD
• Bachelor's degree in Computer Science, Information Systems, or a related field

Nice to Have:
Experience with Snowflake Cortex, semantic views, or warehouse-native LLM tooling
Experience building or extending Model Context Protocol (MCP) servers
Experience with React and data visualization libraries
Certifications across cloud, data, or CI/CD platforms

Interview Process:
Two-stage interview process conducted directly with the client's engineering team.

Please note we are unable to offer employer sponsorship for this role.

Accessibility Statement:
We make an active choice to be inclusive towards everyone every day. Please let us know if you require any accessibility adjustments through the application or interview process.

Our Commitment to Diversity, Equity, and Inclusion:
Signify's mission is to empower every person, regardless of their background or circumstances, with an equitable chance to achieve the careers they deserve. Building a diverse future, one placement at a time.

Check out our DE&I page here.