Description :

- Full Stack .NET Engineer (Agentic AI)

Experience :

- 610 Years

Location :

- Remote Offshore India (Strict Requirement)

Duration :

- 6+ Months

Role Summary :

We are seeking a cutting-edge Full Stack .NET Engineer with a specialized focus on Agentic AI to drive two strategic workstreams: the development of autonomous AI agent solutions and the ML-driven performance assessment of newly acquired technologies.

This is a high-impact, remote role requiring a strict 100% overlap with US EST business hours. You will architect and build sophisticated full-stack applications using .NET (Blazor/React), while leveraging Python and LLM orchestration frameworks to create self-reasoning agents.

This role is designed for a "Modern Engineer" who is an expert at using AI coding assistants (GitHub Copilot, Claude) to accelerate delivery.

Whether you are building RAG-based systems or working with vectorized data models, your mission is to transform complex business problems into autonomous AI-driven realities.

Responsibilities :

- Agentic AI Architecture: Design and implement autonomous agent solutions capable of multi-step reasoning, tool-use, and self-correction to solve complex business opportunities.

- Full-Stack Feature Development: Architect responsive and stateful frontends using Blazor (or React) and robust backend services using .NET Core.

- Machine Learning Assessments: Utilize ML models and Agentic AI capabilities to evaluate the performance, code quality, and technical debt of existing business acquisitions.

- AI Orchestration: Develop and refine agentic workflows using Python and popular frameworks (e.g., Semantic Kernel, AutoGen, or LangGraph) to integrate with LLMs.

- RAG & Vector Integration: Implement Retrieval-Augmented Generation (RAG) patterns using vectorized LLMs and vector databases to provide agents with contextual enterprise knowledge.

- AI-Assisted Engineering: Actively use and optimize GitHub Copilot and Claude for rapid prototyping, refactoring, and automated testing, following specific tech-stack instructions.

- Azure Cloud Governance: Leverage Azure OpenAI Service and Azure's cloud ecosystem to deploy and scale AI solutions securely.

- Technical Communication: Clearly articulate complex AI concepts and architectural decisions to US-based stakeholders, incorporating feedback iteratively.

- Predictive Performance Modeling: Build agents that can analyze system performance trends and provide intelligent, automated insights for technical leadership.

- Documentation & Knowledge Sharing: Meticulously document agentic prompts, system architectures, and ML assessment rubrics to ensure transparency across distributed teams.

Technical Requirements:

- .NET Mastery: 6+ years of experience in Full Stack .NET development, with deep knowledge of C#, .NET Core, and Web API.

- Frontend Versatility: Proficiency in Blazor or React for building modern, component-based user interfaces.

- AI/LLM Engineering: Hands-on experience building Agentic AI solutions (agents that use tools/APIs to complete tasks).

- Python Scripting: Strong working knowledge of Python for AI modeling, data manipulation, and integration tasks.

- Advanced Coding Tools: Expert-level familiarity with GitHub Copilot, Claude, and other AI-driven development accelerators.

- Cloud Infrastructure: Practical experience with Azure services, specifically surrounding AI and containerized deployments.

Preferred Skills :

- Vector Databases: Experience with vectorized LLM implementations and vector stores (e.g., Pinecone, Milvus, or Azure AI Search).

- Reasoning Frameworks: Familiarity with advanced prompt engineering techniques (Chain-of-Thought, ReAct) to reduce AI hallucination.

- Problem-Solving Acumen: Ability to deconstruct "Evaluation of Opportunities" into logical, executable technical workstreams.

- Communication Mastery: Strong verbal and written English skills, critical for navigating US-India cross-cultural stakeholder management.

- Adaptability: Comfort with shifting priorities between building new AI products and auditing legacy machine learning systems.