Founding Context Engineer (AI Infrastructure)
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 Context Engineer (AI Infrastructure)
Location: New York City (On-site)
Company Stage of Funding: Pre-Seed ($3.3M), Early Product-Market Fit
Office Type: Onsite
Salary: $140,000 – $220,000 + Equity
Company Description
We’re representing a pre-seed startup building the infrastructure layer for modern go-to-market (GTM) systems. Their vision is to create “ambient automation” — systems that understand business context and execute intelligently without manual orchestration.
They is building a universal API for B2B businesses, replacing fragmented integrations across dozens of tools with a unified Context API. Their platform enables AI systems to access, reason over, and act on structured business context reliably — solving one of the core limitations of today’s AI systems.
Backed by top investors and a small, senior team from companies like Uber, Lyft, and Capchase, this company is tackling foundational problems in data infrastructure, semantic modeling, and AI-native system design. This is a ground-floor opportunity to define entirely new paradigms in how AI interacts with enterprise data.
What You Will Do
As a Founding Context Engineer, you will build the core infrastructure layer that enables AI systems to reliably access and reason over business context in production.
Key responsibilities include:
- Design and build our Context Management API, enabling structured context across workflows
- Develop new data access patterns that move beyond SQL toward semantic querying for AI systems
- Build retrieval and reasoning pipelines that understand business context before querying data
- Architect self-healing data models that automatically improve based on usage and feedback
- Develop semantic modeling infrastructure that translates business questions into precise, verifiable queries
- Build systems for identity resolution and data unification across dozens of enterprise tools
- Design knowledge graphs and context systems that evolve as business data changes
- Work closely with founders and customers to iterate rapidly on core infrastructure and product direction
Ideal Background
- 3+ years of experience building production systems
- Experience working with LLMs, retrieval systems, embeddings, or vector databases
- Familiarity with knowledge graphs or semantic data systems
- Experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex) or multi-agent systems
- Strong understanding of data infrastructure, including data warehouses (Snowflake, BigQuery) and semantic layers (dbt)
- Experience building or working with production ML systems (monitoring, evaluation, versioning)
- Strong backend engineering skills in Python or similar languages
- Comfortable working in fast-moving, ambiguous, zero-to-one environments
Preferred
- Experience with enterprise data systems (Salesforce, Segment, HubSpot, Gong, etc.)
- Familiarity with workflow orchestration tools (Airflow, Prefect)
- Experience with graph databases or advanced knowledge graph systems
- Experience building real-time data pipelines or streaming systems
- Exposure to multi-agent systems (LangGraph, CrewAI)
- Experience working with reverse ETL tools or data activation platforms
Compensation and Benefits and Other Things
- Base Salary: $140K – $220K
- Equity: Meaningful early-stage equity
- Work Setup: Onsite in New York City
Additional Highlights:
- Founding engineer role (engineer #5–6) with direct impact on company trajectory
- Work directly with experienced founders and early customers
- Opportunity to define new paradigms in AI + data infrastructure
- High ownership, rapid iteration, and first-principles engineering culture