AI Application Engineer

Software Guidance & Assistance, Inc., (SGA), is searching for an AI Application Engineer for a contract assignment with one of our premier Infrastructure Services clients. This role will be remote.

Responsibilities :

Seeking an AI Engineer to help design, test, optimize, and support AI-powered agent experiences across customer and internal business workflows. This role combines prompt engineering, agent orchestration, quality assurance, evaluation framework development, and AI observability.

The ideal candidate is curious, analytical, and hands-on, with experience working with Large Language Models (LLMs), prompt design, testing methodologies, and modern software development practices. You will partner closely with product managers, software engineers, architects, and business stakeholders to improve agent behavior, reliability, accuracy, and user experience.

• Prompt Engineering & Agent Design

• Design, develop, and iterate on AI agent logic for business use cases.
• Create, test, and optimize prompts, system instructions, tools, and workflows to improve agent performance.
• Conduct prompt experiments and A/B testing to measure effectiveness.
• Analyze agent responses and refine prompting strategies for accuracy, consistency, groundedness, and user satisfaction.
• Document prompt patterns, reasoning frameworks, reusable templates, and agent design decisions.

• Collaborate with engineering teams to deploy prompt and agent updates through established SDLC processes.

• AI Quality Assurance & Testing

• Design and execute comprehensive test plans covering AI agents, web applications, APIs, and backend services.
• Develop evaluation frameworks and scoring methodologies for AI output quality.

• Create test cases covering:

• Accuracy
• Hallucination detection
• Safety
• Tone and style adherence
• Instruction following
• Context retention

• Response consistency

• Perform regression testing for prompt and model changes.

• Track, prioritize, validate, and retest defects using Azure DevOps.

• AI Evaluation & Observability

• Utilize Arize or similar observability platforms to monitor model and agent performance.
• Analyze user interactions and evaluation results to identify trends and improvement opportunities.

• Develop quality metrics and dashboards for:

• Accuracy
• Relevance
• Latency
• User satisfaction
• Defect rates

• Prompt performance

• Investigate production issues and recommend prompt, workflow, or architectural improvements.

• Software Engineering & Integration

• Support integration of AI capabilities into enterprise applications and workflows.
• Collaborate with developers to validate API integrations, retrieval pipelines, and agent workflows.
• Assist in CI/CD deployment and release validation activities using Azure DevOps.

• Create and maintain automated testing assets where appropriate.

• Documentation & Collaboration

• Maintain documentation for prompts, evaluation methodologies, testing procedures, and agent configurations.
• Participate in sprint planning, backlog refinement, and Agile ceremonies.
• Communicate findings and recommendations to technical and non-technical stakeholders.
• Share best practices and lessons learned across the team.

Required Skills :

• Bachelor’s degree in Computer Science, Engineering, Information Systems, or related field.
• 5-10 years of experience in software engineering, QA engineering, automation testing, business systems analysis, or related technical roles.
• 1+ years of hands-on experience with Generative AI, LLMs, prompt engineering, or conversational AI solutions.
• Experience working with Azure DevOps or similar Agile delivery platforms.
• Experience designing and executing structured test plans.
• Strong analytical and troubleshooting skills.
• Experience working with APIs and JSON data structures.
• Excellent written and verbal communication skills.

• AI & GenAI

• Prompt Engineering
• Agent Design
• AI Evaluation Frameworks
• RAG Concepts
• LLM Testing
• AI Quality Assurance
• AI Observability

• Prompt Optimization

• Tools

• Arize AI
• Azure DevOps
• Azure OpenAI
• Git
• Postman
• Jira (optional)

• Power BI (optional)

• Development

• Python
• SQL
• REST APIs
• JSON
• Test Automation Frameworks

Preferred Skills :

• Experience with Arize AI or comparable AI observability tools.
• Experience with Azure OpenAI, OpenAI, Anthropic, Gemini, or other LLM platforms.
• Knowledge of Retri…