About the Role

We are seeking an innovative AI Engineer with strong .NET expertise to bridge the gap between enterprise backend engineering and up-to-date Artificial Intelligence. In this role, you will lead the integration of Large Language Models (LLMs), AI agents, and intelligent workflows into high-performance .NET applications using modern enterprise frameworks.

You will work closely with product and data engineering teams to design, build, and deploy enterprise-grade AI solutions, leveraging C#, Semantic Kernel, Azure OpenAI, and vector database architectures.

Key Responsibilities

- AI Architecture & Integration: Design, build, and deploy AI-driven features, RAG pipelines (Retrieval-Augmented Generation), and agentic workflows inside .NET Core / C# enterprise applications.
- Framework Implementation: Utilize Microsoft Semantic Kernel or LangChain to orchestrate LLM prompts, memory state, function calling, and vector search tools inside backend API pipelines.
- API & Backend Engineering: Build scalable, secure RESTful APIs, gRPC services, and microservices using .NET Core / .NET 8+ and C#.
- Vector Search & Data Engineering: Implement and query vector databases (e.g., Azure AI Search, Pinecone, Qdrant, or Pgvector) for semantic retrieval and context augmentation.
- Model Optimization & Fine-Tuning: Evaluate, benchmark, and optimize LLMs (OpenAI GPT, Llama, Claude) for latency, token efficiency, hallucination reduction, and accuracy.
- MLOps & Cloud Deployment: Deploy AI services on Azure (Azure AI Studio, Azure Web Apps) using CI/CD pipelines, containerization (Docker), and automated testing practices.
- Collaboration: Work with cross-functional product, security,



and data science teams to translate business requirements into secure, high-performing AI products.

Required Skills & Qualifications

- Education: Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Information Technology, or a related field.
- Experience: 2 to 5 years of software engineering experience, with at least 1+ years focused on implementing AI models, LLM pipelines, or machine learning in production.
- .NET Mastery: Expert knowledge of C#, .NET Core / .NET 8+, Entity Framework Core, LINQ, and asynchronous programming.
- Generative AI Stack: Demonstrated hands-on experience with Microsoft Semantic Kernel, LangChain, OpenAI APIs, Azure OpenAI Service, or local LLM deployments.
- RAG & Vector DBs: Solid experience with RAG architecture, embeddings, prompt engineering, and vector search engine integration (Azure AI Search, Qdrant, Pinecone, or Milvus).
- Database Skills: Strong proficiency with SQL (MS SQL Server / PostgreSQL) and NoSQL databases.
- Cloud & DevOps: Hands-on experience with Microsoft Azure (Azure App Services, Key Vault, Cognitive Services), Docker, and Git/GitHub Actions.
- Communication: Exceptional verbal and written communication skills to explain complex AI capabilities to both technical and business stakeholders.

Nice-to-Have

- Microsoft Certification: Azure AI Engineer Associate (AI-102).
- Familiarity with Python for quick AI prototyping or data science pipeline validation.
- Experience with AI safety, content guardrails, governance frameworks, and data privacy standard enforcement.

Pay: ₹50,000.00 - ₹150,000.00 per month

Work Location: In person

📌 AI Engineer (Thane)
🏢 Techlicious Design u0026 Development
📍 Thane