Native AI Engineer for STRIDE

Role Summary

We are seeking a highly skilled AI Native Engineer who can independently design, build, and deliver production-ready Generative AI and Agentic AI solutions. The ideal candidate should possess robust software engineering fundamentals, hands-on experience with modern AI technologies, and the ability to take a business problem from ideation through production deployment.

The candidate should have practical experience in LLM engineering, Retrieval-Augmented Generation (RAG), Agentic AI architectures, AI application development frameworks, Azure AI services, security, observability, and AI quality evaluation. The role demands expertise in building reliable, scalable, secure, and cost-efficient AI solutions while following SSDLC best practices.

Key Responsibilities

AI Solution Design & Development

- Design, develop, and deploy enterprise-grade Generative AI and Agentic AI applications.
- Analyze business problems and identify the optimal AI architecture and implementation approach.
- Build production-ready AI applications leveraging Large Language Models (LLMs), RAG, and autonomous agent frameworks.
- Optimize prompt engineering, context management, token consumption, and overall application performance.
- Develop reusable AI services, APIs, and backend components.

LLM Engineering

- Integrate and manage Large Language Model APIs.
- Design effective prompting strategies and structured output generation.
- Implement context window management and conversation memory patterns.
- Optimize LLM interactions for accuracy, performance, and cost efficiency.

RAG & Knowledge Systems

- Design and implement Retrieval-Augmented Generation solutions.
- Develop vector-based search architectures using embeddings and semantic retrieval techniques.
- Configure and optimize Azure AI Search and vector databases.
- Implement grounding, reranking, and retrieval strategies to improve response quality.
- Build and maintain enterprise knowledge repositories.

Agentic AI Development

- Design autonomous and deterministic AI agents to solve business problems.
- Implement tool calling, orchestration, workflow automation,



and multi-agent collaboration.
- Develop agent memory and state management capabilities.
- Build knowledge graph-driven intelligent systems where appropriate.
- Engineer scalable agentic workflows using industry-standard frameworks.

Production Engineering & Operations

- Follow Secure Software Development Lifecycle (SSDLC) practices.
- Implement authentication, authorization, identity management, and AI safety controls.
- Establish observability, monitoring, tracing, and logging standards.
- Optimize application reliability, scalability, performance, and operational costs.
- Deploy AI workloads to production environments and support continuous improvements.

AI Quality & Governance

- Define and execute AI evaluation frameworks.
- Perform hallucination testing, groundedness assessments, and output validation.
- Implement monitoring and tracing mechanisms for model behavior.
- Measure and improve model performance using evaluation metrics and feedback loops.
- Ensure governance, compliance, and responsible AI practices are followed.

Mandatory Skills

Core Software Engineering

- Python and/or C#
- REST API Development
- Backend Engineering
- Git Version Control
- Software Development Life Cycle (SDLC / SSDLC)
- Application Architecture & Design Patterns

LLM Engineering

- Large Language Model APIs
- Prompt Engineering
- Structured Output Design
- Context Management
- Token Optimization
- Conversational AI Development

Retrieval-Augmented Generation (RAG)

- Azure AI Search
- Embeddings
- Vector Search
- Retrieval Mechanisms
- Reranking
- Grounding Techniques
- Knowledge Retrieval Systems

Agentic AI

- Agent Design and Development
- Tool Calling
- Agent Orchestration
- Multi-Agent Systems
- Workflow Automation
- State Management




- Knowledge Graphs
- Deterministic and Autonomous Agents

AI Frameworks

- Semantic Kernel
- LangGraph
- LangChain
- Agent Frameworks
- Microsoft Foundry Agent SDK
- Model Context Protocol (MCP)

Cloud AI Platforms

- Azure AI Foundry
- Azure OpenAI Services
- Equivalent Cloud AI Platforms

Production Engineering

- Security & AI Guardrails
- Identity & Access Management
- Observability
- Reliability Engineering
- Scalability Engineering
- Cost Optimization

AI Quality Engineering

- AI Evaluations (Evals)
- Hallucination Testing
- Groundedness Validation
- Tracing & Monitoring
- Performance Measurement

Good-to-Have Skills

- Knowledge Graph Engineering
- Prompt Flow
- Azure Functions
- Event-Driven Architectures
- Containerization (Docker/Kubernetes)
- MLOps Concepts
- CI/CD for AI Applications
- Vector Database Technologies

Nice-to-Have Skills

- Experience building enterprise-scale AI copilots and assistants
- Experience with multimodal AI applications
- Experience working with Azure ecosystem services
- Experience mentoring development teams
- Experience leading AI solution architecture discussions
- Understanding of Responsible AI and AI Governance frameworks

Soft Skills

- Strong analytical and problem-solving abilities
- Excellent communication and stakeholder management skills
- Ability to independently drive solution design and delivery
- Strong collaboration and teamwork skills
- Ability to translate business requirements into AI-driven solutions
- Continuous learning mindset with passion for emerging AI technologies

Preferred Candidate Profile

- Proven experience delivering production-ready GenAI applications.
- Strong hands-on expertise in LLMs, RAG architectures, and Agentic AI solutions.
- Experience building secure, scalable, and observable AI systems.
- Ability to independently own the complete AI application lifecycle from design to deployment.
- Strong understanding of software engineering best practices and SSDLC.
- Experience optimizing AI applications for quality, performance, and cost efficiency.

📌 Senior AI Engineer (India)
🏢 NewVison
📍 India