Tests AI model outputs and application functionality. Validates data accuracy, business logic and system performance. - Design and execute test plans covering AI model outputs, data correctness, and application functionality.

• Create automated tests for APIs and UI where appropriate; maintain regression suites.
• Validate business logic, edge cases, and non-functional requirements (performance, reliability).
• Establish evaluation criteria for AI components (accuracy, hallucination checks, guardrail adherence).
• Triage defects, document reproducible steps, and partner with engineers to resolve issues.
• Contribute to release readiness, quality gates, and continuous improvement of testing practices.

AI-driven Agentic Software Engineer (Fullstack)
Rate:- 60-70/Hr on C2C
Location: Onsite (Hartford, CT, OR Minneapolis, MN) locals preferred.

Client: Virtusa / Health Care Company

JD:-Build full-stack applications that integrate AI/ML outputs into user-facing and backend workflows.
Develop APIs and services that orchestrate model inference, prompt flows, and agent/tool integrations.
Leverage AI coding assistants (e.g., GitHub Copilot, agentic IDEs) to accelerate delivery while maintaining quality.
Implement UI/UX experiences for AI-enabled features (explanations, feedback loops, human-in-the-loop controls).
Apply secure SDLC practices: code reviews, testing, dependency management, and vulnerability remediation.
Partner with architects and platform teams to align to standards and reuse shared components.
5+ years building production software (backend and/or frontend) in Java/Python/.NET ecosystems.
Experience with web frameworks and modern UI (React or similar) and REST API development.
Working knowledge of CI/CD, Git workflows, and automated testing.
Comfort integrating with ML services, LLM/agent runtimes, or data platforms via APIs.
Strong problem-solving skills and ability to deliver iteratively in an agile environment.
Experience building internal tools or copilots with prompt engineering and tool/function calling.
Experience with observability for AI features (quality metrics, prompt/model versioning).
UX experience designing AI interactions and feedback capture.Fullstack Integration, LLM Orchestration, and User Experience.
Mandatory Skills (The "Must-Haves")
LLM Orchestration: Mastery of frameworks like LangChain or LangGraph to manage multi-turn agentic workflows.
GenAI Implementation: Practical experience with RAG (Retrieval-Augmented Generation) using vector databases like FAISS, Pinecone, or Azure Cognitive Search.
API & Microservices: Advanced development of services that orchestrate model inference and tool integrations using FastAPI or Node.js.
AI Coding Assistants: Effective use of GitHub Copilot or agentic IDEs to accelerate delivery without sacrificing code quality.
UI/UX for AI: Ability to build "human-in-the-loop" controls and feedback loops into the frontend.

Good-to-Have Skills
Vector Embeddings: Deep understanding of embedding models (e.g., OpenAI Ada) and chunking strategies.
Containerization: Proficiency in Docker and Kubernetes (AKS/EKS) for sustaining high throughput (1K+ RPS).
Observability: Experience with OpenTelemetry or Azure Monitor to track agent reliability and response accuracy.