Generative AI Developer

Valiant Technologies LLC; Columbus (OH); On-site; USD 130,000 - 190,000; Full time

Job summary

Valiant Technologies LLC is seeking a software engineer focused on AI-enabled solutions in Columbus, OH. You will design prompts, build robust AI features, and integrate LLMs across systems to deliver measurable business value.

You will collaborate with product, data science, cloud, security, and other stakeholders to implement guardrails, safety controls, and scalable architectures while maintaining a strong emphasis on security and responsible AI practices.

Qualifications

• Experience building scalable Python applications with AI components.
• Strong knowledge of API design, REST, and microservices.
• Experience with CI/CD, automated testing, and Git workflows.
• Hands-on with major LLM providers and privacy/safety practices.
• Experience with retrieval-augmented generation and related frameworks.

Responsibilities

• Design effective system prompts, instructions, structured output templates, and evaluation-driven prompt improvements for accuracy, consistency, and cost efficiency.
• Implement AI guardrails, content safety controls, privacy practices, responsible AI workflows, and human-in-the-loop review patterns.
• Establish evaluation frameworks to measure accuracy, relevance, latency, cost, and user satisfaction.
• Monitor production systems and continuously optimize performance.
• Translate complex AI concepts into business-focused solutions.
• Collaborate effectively with product managers, data scientists, cloud engineers, security teams, and stakeholders.

Skills

Python development

API design

CI/CD

Git version control

LLM integration

Multi-agent AI

AI guardrails

Tools

Azure OpenAI

OpenAI

Anthropic Claude

Google Gemini

LangChain

LlamaIndex

Semantic Kernel

LangGraph

Job description

Job Description:

The role combines software engineering expertise with modern AI technologies to deliver scalable, secure, and responsible AI solutions that create measurable business value.

Key Responsibilities

• Design effective system prompts, instructions, structured output templates, and evaluation-driven prompt improvements for accuracy, consistency, and cost efficiency.
• Implement AI guardrails, content safety controls, privacy practices, responsible AI workflows, and human-in-the-loop review patterns.
• Establish evaluation frameworks to measure accuracy, relevance, latency, cost, and user satisfaction.
• Monitor production systems and continuously optimize performance.
• Translate complex AI concepts into business-focused solutions.
• Collaborate effectively with product managers, data scientists, cloud engineers, security teams, and stakeholders.

Required Qualifications

• Strong proficiency in Python for application development, API integrations, and AI workflow implementation.
• Experience building REST APIs, microservices, and backend services.
• Strong understanding of software engineering best practices, version control with Git, automated testing, and CI/CD.
• Hands-on experience with LLM providers such as Azure OpenAI, OpenAI, Anthropic Claude, Google Gemini, and open-source models.
• Experience implementing chat applications, AI copilots, agents, function calling, tool integration, and multi-modal AI capabilities.
• Experience building Retrieval‑Augmented Generation (RAG) solutions and proficiency with frameworks like LangChain, LangGraph, LlamaIndex, and Semantic Kernel.

Preferred Qualifications

• 5+ years of software engineering experience.
• 2+ years of experience building Generative AI or Machine Learning solutions.
• Experience developing enterprise AI applications in healthcare, finance, or large‑scale business environments.
• Microsoft Azure certifications are preferred.
• Agentic AI development and multi‑agent orchestration.
• Fine‑tuning, model customization, and evaluation pipelines.
• Experience with AI observability frameworks such as LangSmith or PromptFlow.
• Knowledge of graph‑based retrieval patterns.
• Experience in healthcare AI, privacy, safety, and Responsible AI.

We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.