AI Product Engineer

Remote (United States)

Job Details

Location: United States (Remote)

Workplace: Remote

Employment Type: Full-Time

Core Areas: Large Language Models (LLMs), AI Product Development, Production AI Systems, Data Engineering, ETL Pipelines, LLM Evaluation, Cloud Infrastructure, Workflow Automation

Compensation: Engineer: $90,000–$150,000 annually; Senior Engineer: $150,000–$180,000 annually

Travel: Occasional client travel required.

About the Role

This AI Product Engineer opportunity focuses on designing, building, deploying, and improving production-ready AI applications for enterprise clients. The position involves end-to-end ownership of AI product development, from requirements gathering and rapid prototyping with large language models (LLMs) to production deployment, data integration, evaluation, and ongoing optimization. Projects include enterprise document processing, workflow automation, computer vision, and financial research tools.

The role combines software engineering, applied AI, data engineering, and cloud infrastructure with direct technical ownership of client engagements. Successful candidates bring strong programming and system design fundamentals, practical experience shipping LLM-powered products, and the ability to evaluate AI reliability and performance. Work spans financial services, healthcare, and enterprise environments, requiring attention to security, data privacy, production reliability, and infrastructure costs.

What You'll Do

• Lead end-to-end development of AI-powered products, taking solutions from initial concept and technical design through production deployment and ongoing improvements.
• Gather technical and business requirements, evaluate stakeholder requests, define implementation approaches, and prioritize development activities based on product needs.
• Build and rapidly prototype applications using large language models (LLMs), then transform working prototypes into reliable production systems.
• Develop AI application evaluation processes, including LLM output assessments, error analysis, and testing to improve solution quality and reliability.
• Design and implement data ingestion workflows, data models, data architecture, ETL processes, and production data pipelines for enterprise applications.
• Integrate AI applications with existing systems, services, and enterprise workflows.
• Serve as the primary technical contact during client engagements, working directly with client engineers and explaining technical decisions to executives and business stakeholders.
• Implement product instrumentation, analytics, funnel metrics, and error analysis to measure application behavior and guide improvements based on actual usage.
• Manage production reliability, application security, authentication, secrets management, and personally identifiable information (PII) handling.
• Monitor infrastructure efficiency and cloud resource consumption to support secure, reliable, and cost-conscious deployments.
• Apply debugging, performance analysis, and system design practices to resolve production issues and improve application scalability.
• Document technical decisions, engineering findings, implementation lessons, and product insights for technical teams, clients, and public audiences.

Qualifications

Required Experience

• Demonstrated experience building, deploying, and maintaining software applications used in real-world production environments.
• Hands-on experience delivering at least one LLM-powered application or product with actual users, ideally including output evaluation and error analysis.
• Practical experience with data engineering, including data modeling, data architecture, ETL processes, and pipeline development.
• Experience developing applications that require production deployment, systems integration, security controls, and operational reliability.
• Ability to take ownership of ambiguous technical projects, define requirements, establish implementation priorities, and deliver working solutions with limited supervision.
• Experience translating client or stakeholder discussions into clear technical requirements, development tasks, and actionable implementation plans.

Required Skills

• Strong programming, debugging, and software system design skills, including the ability to identify failure conditions and troubleshoot complex application behavior.
• Practical knowledge of large language models (LLMs), their capabilities, limitations, and effective integration into production AI applications.
• Ability to develop LLM-powered prototypes and implement the data pipelines, integrations, and evaluation processes needed for production readiness.
• Proficiency in data modeling, data architecture, ETL workflows, and data pipeline implementation using tools such as Airflow, Dagster, Inngest, Prefect, or comparable technologies.
• Understanding of web application architecture, authentication, web security, and secure handling of sensitive information.
• Ability to diagnose database performance issues, including inefficient queries, N+1 query patterns, and unnecessary database joins.
• Knowledge of CI/CD practices, application deployment, and cost-aware infrastructure management on a major cloud platform.
• Experience using modern AI-assisted development tools, such as Claude Code, with customized engineering workflows.
• Ability to evaluate application performance through analytics, funnel metrics, error analysis, and production usage data.
• Strong technical judgment when evaluating AI system reliability, data quality, security requirements, and deployment trade-offs.
• Ability to communicate technical concepts clearly to engineers, executives, and other stakeholders.
• Strong written communication skills, including technical documentation, clear task definition, and concise summaries of complex client requirements.

Preferred Qualifications

• Specialized expertise in financial services, healthcare, or enterprise and contact-center AI applications.
• Experience representing engineering teams in senior-level client discussions and technical engagements.
• Strong proficiency in TypeScript and a preference for developing applications with TypeScript-based technology stacks.
• Experience designing and implementing observability capabilities for AI-powered products.
• Active engagement with the applied AI engineering community.
• Experience independently developing and launching a product from concept to initial adoption, followed by improvements based on real user feedback.
• Experience working as a solo engineer or founding engineer with responsibility for product delivery and outcomes.
• Deep technical expertise in at least one area, such as machine learning, full-stack development, data engineering, or security, supported by broader engineering capabilities.

Benefits:

• Medical, dental, and vision coverage.
• Flexible paid time off (PTO).
• Health Flexible Spending Account (FSA) and Health Savings Account (HSA) benefits.
• Life insurance coverage.
• Flexible working arrangements with an emphasis on completed work and project outcomes.