Founding Full-Stack Engineer

Recruiting from Scratch; New York (NY); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Early equity

Direct founder access

Define new AI infra

High technical ownership

In-person collaboration

Career growth

Job summary

Recruiting from Scratch is seeking a founding Full-Stack Engineer in New York City to build and scale core platform services for context-aware AI systems. You will develop full-stack applications, APIs, data systems, and customer-facing interfaces, and design semantic query systems enabling AI agents to reason over business data.

This is an early engineering hire with high ownership and direct collaboration with founders.

Qualifications

• 3+ years of experience building and shipping production software systems.
• Strong full-stack engineering across backend, APIs, databases, and modern web applications.
• Experience with LLMs, retrieval systems, embeddings, knowledge graphs, or AI infrastructure.
• Hands-on ML system deployment in production, including evaluation, monitoring, and model lifecycle management.
• Familiarity with LLM orchestration frameworks, agent architectures, or multi-agent systems.
• Systems-thinking mindset for complex data flows and business processes.
• Experience operating in ambiguous, fast-moving startup environments.
• Excellent communication skills and ability to work directly with customers and stakeholders.
• High ownership mentality with a track record of independently driving projects from concept through deployment.

Responsibilities

• Build and scale core platform services that power context-aware AI systems in production.
• Develop full-stack applications across backend infrastructure, APIs, data systems, and customer-facing interfaces.
• Design and implement semantic query systems that enable AI agents to reason about business data beyond traditional database access patterns.
• Build retrieval systems, knowledge infrastructure, and context management layers that support enterprise AI workflows.
• Create self-improving data models and feedback systems that evolve alongside customer usage patterns.
• Develop integrations across enterprise systems, data warehouses, CRMs, analytics platforms, and business applications.
• Design and maintain APIs that translate natural language intent into structured, verifiable outcomes.
• Partner directly with customers to understand complex business workflows and transform them into scalable platform capabilities.
• Contribute to architecture decisions across product, infrastructure, and AI systems as an early member of the engineering team.
• Ship quickly in a highly iterative environment while maintaining strong engineering standards.

Skills

Full-stack development

Backend APIs

Databases

LLMs knowledge

Production software

Startup experience

Customer interaction

Python

JavaScript/TypeScript

Tools

LLM orchestration frameworks

Embeddings

Knowledge graphs

Vector databases

Job description

Who is Recruiting from Scratch: Recruiting from Scratch is a specialized talent firm dedicated to helping companies build exceptional teams. We partner closely with our clients to deeply understand their needs, then connect them with top-tier candidates who are not only highly skilled but also the right fit for the company’s culture and vision. Our mission is simple: place the best people in the right roles to drive long-term success for both clients and candidates.https://www.recruitingfromscratch.com/

Title of the Role: Founding Full-Stack Engineer

Location: New York City

Company Stage of Funding: Venture-Backed Pre-Seed AI Infrastructure Startup

Office Type: In-Office

Company Description

We're representing a venture-backed AI infrastructure startup building the next generation of context management systems for AI applications. Their platform serves as a universal context layer that enables AI agents to interact reliably with enterprise systems, business data, and organizational knowledge.

Backed by leading early-stage investors and founded by a highly technical team from top technology companies and research institutions, the company is tackling one of the most important challenges in AI today: enabling agents to reason over complex enterprise environments with accurate, structured context rather than relying on incomplete or hallucinated information.

As an early engineering hire, you'll help define entirely new patterns for how AI systems access, understand, and act on business data.

What You Will Do

• Build and scale core platform services that power context-aware AI systems in production.
• Develop full-stack applications across backend infrastructure, APIs, data systems, and customer-facing interfaces.
• Design and implement semantic query systems that enable AI agents to reason about business data beyond traditional database access patterns.
• Build retrieval systems, knowledge infrastructure, and context management layers that support enterprise AI workflows.
• Create self-improving data models and feedback systems that evolve alongside customer usage patterns.
• Develop integrations across enterprise systems, data warehouses, CRMs, analytics platforms, and business applications.
• Design and maintain APIs that translate natural language intent into structured, verifiable outcomes.
• Partner directly with customers to understand complex business workflows and transform them into scalable platform capabilities.
• Contribute to architecture decisions across product, infrastructure, and AI systems as an early member of the engineering team.
• Ship quickly in a highly iterative environment while maintaining strong engineering standards.

Ideal Background

• 3+ years of experience building and shipping production software systems.
• Strong full-stack engineering capabilities with experience across backend systems, APIs, databases, and modern web applications.
• Experience working with LLMs, retrieval systems, embeddings, vector databases, knowledge graphs, or related AI infrastructure.
• Hands‑on experience deploying machine learning systems in production, including evaluation, monitoring, and model lifecycle management.
• Familiarity with LLM orchestration frameworks, agent architectures, or multi‑agent systems.
• Strong systems‑thinking mindset with the ability to reason about complex data flows and business processes.
• Experience operating in ambiguous, fast‑moving startup environments.
• Excellent communication skills and ability to work directly with customers and stakeholders.
• High ownership mentality with a track record of independently driving projects from concept through deployment.

Preferred

• Experience with enterprise data platforms, warehouses, or analytics ecosystems.
• Familiarity with semantic layers, modern data stacks, and data modeling frameworks.
• Experience building agentic workflows or orchestration systems.
• Knowledge of graph databases, knowledge graphs, or semantic search systems.
• Experience with real‑time data pipelines, event‑driven architectures, or streaming systems.
• Background working on AI infrastructure, developer platforms, or enterprise SaaS products.
• Previous startup experience as an early engineer or founding team member.
• Experience building 0→1 products and shipping customer-facing features in rapidly evolving environments.

Compensation and Benefits

• Meaningful early‑stage equity ownership.
• Direct collaboration with founders, customers, and senior engineering leadership.
• Opportunity to help define a new category of AI infrastructure.
• Fast-paced, highly iterative environment with significant technical ownership.
• In‑person engineering culture focused on collaboration, rapid execution, and first‑principles thinking.
• Significant career growth opportunity as one of the earliest engineering hires.