KlariVis is a well-known and respected provider of SaaS-based analytics to the banking industry. Our clients rely on us to provide the data and analytics they need today, while also helping guide their data and analytics journey and delivering the analytics services of tomorrow.  

We are looking for a Generative AI Application Engineer that is hands-on, mid-level engineering role focused on building and shipping production generative AI applications, services, agents, and tools directly against large language model APIs. 

Candidates must have generative AI applications running in production today and must be able to name them, describe their own contribution to them, and provide reachable references who can confirm that contribution.  

We are looking for someone with strong software engineering fundamentals, substantial Python and API development experience, strong SQL skills, and meaningful experience building generative AI applications that are currently running in production.  

• KlariVis offers a competitive compensation package including salary, medical, dental, HSA health benefits, 401(k) match, and flexible time off.
• Actual compensation will be determined based on factors including relevant experience, technical expertise, education, certifications, internal equity, and other job-related qualifications. 
• KlariVis is headquartered in Roanoke, Virginia.
• Applicants must be currently based and authorized to work in the United States on a full-time basis. 
• KlariVis does NOT sponsor applicants for work visas. 

What You'll Do

• Design, build, and ship production generative AI features directly against LLM APIs, including prompt construction, structured outputs, tool/function calling, retrieval, context management, and failure handling.
• Build evaluation and regression frameworks to ensure generative AI features continue to perform as models, prompts, and data change.
• Integrate generative AI capabilities with KlariVis product services, APIs, and data models.
• Build and maintain API-based applications and services.
• Write and optimize SQL against relational data models.
• Deploy and operate application components across cloud environments, including virtual machines, containers, object storage, and relational database services.
• Work with Hugging Face models and internally hosted inference engines.
• Collaborate closely with product management, data engineering, and other members of the Modeling and AI team to turn requirements into shipped features. Generative_AI_Application_Engin…
• Participate in code reviews and clearly communicate technical decisions, trade-offs, progress, and blockers.
• Write automated tests and AI evaluation tests.
• Monitor production AI applications for quality, latency, token usage, and cost.
• Contribute to model-based analytics and internal AI initiatives that improve organizational efficiency. 

What We're Looking For

Required Qualifications

• 5+ years of professional software development experience, including hands-on development of API-based applications or services deployed to production.
• 4+ years of hands-on Python development experience.
• 2+ years of substantive generative AI development at the LLM API level, including direct work with model APIs, prompt design, structured outputs, tool/function calling, retrieval, and evaluation.
• Experience helping build at least two non-trivial generative AI applications that are currently running in production.
• Strong SQL skills, including joins, aggregations, window functions, common table expressions, and relational database concepts.
• 4+ years of experience working in a cloud environment across multiple resource types such as VMs, containers, object storage, and relational database services.
• Experience with Git and/or Azure DevOps and solid version-control practices.