About the Company
Purple Squirrel Enterprises has supported startups and global organizations through growth and expansion for more than 19 years, providing recruiting and HR solutions. The company is partnering exclusively with an established SaaS analytics provider serving the banking industry to recruit a Generative AI Application Engineer.
The client helps banks and credit unions turn operational and customer data into actionable business insights. Its Modeling and AI team develops advanced analytics solutions and is expanding its capabilities to deliver production-ready generative AI features within its platform.
About the Role The Generative AI Application Engineer will design, develop, deploy, and maintain production generative AI applications, API-based services, agents, and tools built directly on large language model (LLM) APIs. This is a hands-on, mid-level software engineering role focused on applied generative AI, Python development, API integration, SQL, and production operations rather than AI research or model development alone.
The engineer will collaborate with product management, data engineering, and the internal AI/Modeling team to translate requirements into reliable software features. Development follows an AI-first, specification-driven process, with an emphasis on evaluation, monitoring, security, and responsible handling of sensitive financial data.
Key Responsibilities
Design and deliver production generative AI applications using LLM APIs, including prompt construction, structured outputs, tool and function calling, retrieval, context management, and error handling.
Build and maintain evaluation and regression testing frameworks to assess AI application 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 serving configuration and deployment.
Develop, maintain, and support API-based applications and services throughout the software development lifecycle.
Write and optimize SQL queries for application state, feature data, evaluation datasets, and product analytics.
Deploy and operate application components across virtual machines, containers, object storage, and relational database services, primarily within 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.
Identify opportunities to improve organizational efficiency using generative AI, machine learning models, and heuristics.
Collaborate with product management, data engineering, and AI/Modeling colleagues to deliver features that meet business and technical requirements.
Participate in code reviews and communicate technical decisions, progress, risks, and blockers to team members and stakeholders.
Write automated tests for generative AI applications and machine learning components.
Monitor production applications for accuracy, latency, token consumption, and cost, and participate in production support as needed.
Follow security, data-handling, and change-management practices appropriate for sensitive financial information.
Required Qualifications
At least 5 years of professional software development experience, ideally in a software product organization, including hands-on development of production API-based applications and services.
At least 4 years of hands-on Python development experience, with the ability to explain and defend technical and architectural decisions.
At least 2 years of substantive generative AI development using LLM APIs, including prompt design, structured outputs, tool or function calling, retrieval, and evaluation. No-code or low-code tool assembly alone does not meet this requirement.
Experience building at least two non-trivial generative AI applications that are currently in production, with the ability to explain the business problem, architecture, personal contributions, and evaluation and monitoring approach.
Strong SQL skills, including joins, aggregation, window functions, and common table expressions (CTEs), along with an understanding of relational database performance and role-based access controls.
At least 4 years of experience working across multiple resource types in a hyperscaler environment, including virtual machines, containers, object storage, and relational database services. Microsoft Azure is preferred; equivalent AWS or GCP experience is acceptable.
Proficiency with version control tools and practices, including Git and/or Azure DevOps.
Reachable professional references who can verify the experience described in the posting, including hands-on contributions to production generative AI applications.
Highly Desirable Qualifications
Hands-on experience selecting and evaluating Hugging Face models, including serving formats and quantization options.
Direct experience deploying models for self-hosted LLM inference using technologies such as LightLLM, vLLM, SGLang, TensorRT-LLM, TGI, Ray Serve, Triton, Ollama, llama.cpp, or similar platforms. Experience with gateway and routing layers such as LiteLLM is also relevant.
Experience operating self-hosted inference deployments for production applications, including capacity planning, batching, concurrency, versioning, and monitoring.
Experience developing applications or user interfaces that connect to self-hosted, open-source LLMs through APIs.
Additional Preferred Qualifications
Experience with Amazon Bedrock or Microsoft Foundry, formerly Azure AI Foundry.
Machine learning experience involving feature engineering, model training, and evaluation using Pandas, scikit-learn, or similar tools.
Familiarity with Python charting libraries such as Matplotlib, Seaborn, or Plotly.
Experience with Azure SQL and PySpark for large datasets.
Additional programming experience in C#, Java, or Scala.
React and TypeScript UI development experience; familiarity with AI Elements or shadcn/ui is a plus.
Exposure to banking, financial services, or other regulated data environments.
Professional Reference Requirements
Professional references must be available to verify the experience claimed in the application.
At least one reference is required from each organization where the candidate's production generative AI applications were built and deployed.
References must be able to discuss the candidate's personal contributions, technical decisions, and the application's production performance.
References will be contacted, and any offer is contingent on verification of the candidate's production generative AI experience.
Candidates who are restricted by a former employer's policies or an NDA from sharing certain details should raise the issue during the first interview so an acceptable alternative can be discussed.
Location and Employment Details
Location: United States, Remote
Employment Type: Full-time, W2
Working Hours: Must be able to work remotely in the United States on an East Coast schedule, starting at 8:30 a.m. ET. Pacific Time candidates may start at 6:00 a.m. PT, corresponding to 9:00 a.m. ET, with availability for meetings at 8:30 a.m. ET when needed.
Industry: Financial Technology / Data Analytics SaaS
Reports To: AI/Modeling Team Leadership
Compensation and Benefits
Base Salary: $135,000–$150,000, with potential consideration outside this range for candidates who demonstrably exceed the core requirements, including verified production generative AI experience and strong professional references.
$1,100 per month in company contributions toward eligible pre-tax benefits, including medical, dental, vision, and HSA options.
Medical, dental, and vision coverage, including HSA-compatible plans.
UHC Rewards program offering up to $300 annually for non-HSA participants or $1,000 for HSA participants through wellness activities.
Employer-paid life and accidental death and dismemberment (AD&D) insurance equal to one year's salary, up to $200,000.
Employer-paid short-term and long-term disability coverage.
Voluntary additional life and AD&D, critical illness, accident, and hospital indemnity coverage.
Employee Assistance Program (EAP).
401(k) plan with an employer match of up to 4.5% when employees contribute 6% of salary, with immediate vesting.
Company holidays and a Flexible Time Off (FTO) policy without a fixed PTO cap, coordinated with managers.
Equal Employment Opportunity The client is an equal opportunity employer committed to building a diverse and inclusive team. Applicants from all backgrounds, experiences, and perspectives are welcome.