Generative AI Application Engineer

About the Company

Purple Squirrel Enterprises provides recruiting and HR solutions to startups and global organizations, helping businesses manage hiring and people operations. For this search, Purple Squirrel Enterprises is working exclusively with an established SaaS analytics company serving the banking industry.

The client provides data analytics software that helps banks and credit unions turn operational and customer data into useful business insights. Its internal Modeling and AI team develops advanced analytics capabilities and is expanding its work on production-ready generative AI features for its platform.

About the Role

The client is seeking a Generative AI Application Engineer to design, develop, deploy, and maintain production generative AI applications. This is a hands-on, mid-level software engineering role focused on building applications directly with large language model (LLM) APIs, developing API-based services and AI agents, and supporting the application and data layers behind these features.

The role emphasizes strong Python and SQL skills, practical generative AI development, production deployment, evaluation, and monitoring. The engineer will work with product management, data engineering, and the internal AI/Modeling team to turn requirements into production features and identify opportunities to improve organizational efficiency through AI and model-based solutions.

Candidates must have generative AI applications running in production and be able to explain their individual contributions, technical decisions, and application performance. Professional references will be required to verify this experience.

Key Responsibilities

• Design, build, and deploy production generative AI features using LLM APIs, including prompt construction, structured outputs, tool and function calling, retrieval, context management, and failure handling.
• Develop and maintain evaluation and regression frameworks to assess AI behavior as models, prompts, and data change.
• Integrate generative AI components with existing product services, APIs, and data models.
• Work with Hugging Face models and internally hosted inference engines, including configuring and deploying model-serving infrastructure.
• Design, build, and maintain API-based applications and services throughout the software development life cycle.
• Write and optimize SQL queries against relational data models supporting application state, feature data, evaluation datasets, and product analytics.
• Deploy and operate application components across cloud resources, including virtual machines, containers, object storage, and relational database services, primarily in Microsoft Azure.
• Contribute to analytics product development outside AI and modeling when required.
• Support model-based analytics initiatives, including customer segmentation, churn forecasting, and lifetime value forecasting, in collaboration with senior AI/Modeling team members.
• Identify opportunities to improve internal efficiency using generative AI, models, and heuristics.
• Collaborate with product management, data engineering, and AI/Modeling colleagues to translate requirements into delivered features.
• Participate in code reviews, provide constructive feedback, and incorporate feedback from teammates.
• Communicate progress, technical trade-offs, and blockers clearly to team members and stakeholders.
• Write automated tests for application functionality, generative AI evaluations, and machine learning model assessments.
• Monitor production AI applications for accuracy, latency, token consumption, and cost, and participate in production support as needed.
• Follow security, data-handling, and change-management practices when working with sensitive financial information.

Required Qualifications

• At least 5 years of professional software development experience, ideally within a software product organization, including hands-on development of API-based applications and services deployed in production.
• At least 4 years of hands-on Python development experience, with the ability to explain and justify technical and design decisions.
• At least 2 years of substantial generative AI development at the LLM API level, including prompt design, structured outputs, tool and function calling, retrieval, and evaluation.
• Experience helping build at least two non-trivial generative AI applications that are currently in production.
• Ability to explain the busin…