AI Product Engineer

Responsibilities

Building the "Enterprise Brain" (Architecture & Integration)

• Develop a unified intelligence layer that ingests signals from disparate sources (Product Telemetry, CRM, Call Transcripts, Marketing inputs) and processes them into actionable outputs.
• Build robust integrations/webhooks to push AI-generated insights directly into workflow tools (e.g., pushing "Churn Risk" alerts into Salesforce

AI Logic & Agent Implementation

• Architect "Agentic" workflows where LLMs are granted permission to perform tasks
• Implement advanced RAG to ground AI outputs in company documentation, historical data, and strategic context.
• Ensure rigorous evaluation and guardrails for non-deterministic models to prevent "hallucinations" in critical business workflows.
• Collaborate with Analytics Engineers to ensure the underlying data pipelines support real-time or near-real-time AI applications.
• Maintain security and privacy standards, ensuring that AI agents respect data access permissions across different departments.

Preferred

• Experience working with APIs for major B2B tools (Salesforce, HubSpot, Zendesk, Jira, Marketo).

Role Overview

• We are transitioning our organization to an AI-first operational model. We are seeking an
• AI Product Engineer to architect and build the company’s central intelligence engine.
• In this role, you will be the primary builder of automated intelligence systems
• —tools that not only retrieve insights but actively trigger workflows, and synthesize strategic intel across our entire business landscape.

Role Profile

This is a high-impact, hands-on engineering role requiring a convergence of three distinct skill sets:

Software Engineering (50%)

Building scalable middleware, API integrations, and production-grade applications that connect our data stack to business tools (CRM, Marketing Automation, Support/Ticketing).

AI Engineering (30%)

Implementing Agentic workflows, RAG architectures, and LLMs to process unstructured data at scale.

Data Analytics (20%)

Leveraging SQL and B2B SaaS metrics to ensure all automation is grounded in accurate, governed data.

Key Responsibilities

Data Engineering & Governance

Education

Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.

Software Engineering

3+ years of experience in Python development, with strong proficiency in API development (FastAPI/Django) and building integrations between SaaS platforms.

AI/ML Application

Proven experience building applications using LLM APIs and orchestration frameworks, Experience with "Agent" concepts.

Data Proficiency

Strong SQL skills and familiarity with cloud data warehouses (Snowflake/BigQuery).

Workflow Automation

Experience with tools like Airflow, Zapier/Make (advanced usage), or custom workflow engines.

B2B Domain Expertise

Understanding of the interplay between Sales, Product, and Customer Success.

The "Builder" Mindset

You are comfortable taking a high-level strategic requirement from leadership (e.g., "We need to automate lead qualification") and independently architecting and coding the solution.

Systemic Thinking

You understand how a change in product data schema impacts the downstream marketing automation flow.

Adaptability

You can switch contexts rapidly—from debugging a SQL query for Strategy to refining a prompt for Customer Support automation.