AI Full Stack Developer (.NET + Angular + LLM) | Avendata Group | Remote (India)

Avendata Group; India; À distance; INR 1 200 000 - 3 200 000; Plein temps

Résumé du poste

Avendata Group is seeking an experienced AI Full Stack Developer (2–8 years) to design, build, test, and deploy AI-enabled web applications in a remote Indian setup. You will work with .NET Core, C#, Angular, TypeScript, RESTful APIs, and vector databases to deliver scalable enterprise AI solutions.

You will own AI pipeline integration, RAG workflows, and collaboration with data scientists and QA in an Agile environment, ensuring code quality and security standards.

Qualifications

• Bachelor’s degree in Computer Science, IT, Software Engineering, AI, or related field.
• 2–8 years of progressive experience in full-stack software engineering and enterprise web apps.
• Strong hands-on expertise in .NET Core, C#, OOP, and backend services.
• Comprehensive knowledge of Angular, TypeScript, HTML5, CSS3, and modern frontend development.
• Experience developing AI/LLM apps, Generative AI models, and RAG architectures.
• Proficiency designing, consuming, securing RESTful APIs and distributed microservices.
• Experience with Cursor AI and AI-assisted development tools.
• Excellent English communication and collaborative skills.
• Remote work eligibility in India (immediate joiners or notice period preferred).

Responsabilités

• Design, develop, test, and deploy production-ready full-stack web apps using Angular/TypeScript for frontend architecture.
• Architect and maintain backend microservices, REST APIs, and business logic with .NET Core and C#.
• Build, optimize, and scale RAG pipelines and LLM integration workflows.
• Utilize Cursor AI to accelerate software delivery and code quality.
• Integrate vector databases and embedding models (LlamaIndex, LangChain, Semantic Kernel).
• Perform unit testing, debugging, and performance profiling across full-stack components.
• Collaborate with AI engineers, data scientists, product managers, and QA in Agile sprints.
• Ensure security, standards, and enterprise coding practices; document architecture and APIs.

Connaissances

.NET Core

C#

Angular

TypeScript

RESTful APIs

HTML5

CSS3

AI/LLM integration

RAG pipelines

English communication

Remote work eligibility (India)

Formation

Bachelor’s degree in CS/IT/Software/AI or related field

Outils

Cursor AI

LlamaIndex

LangChain

Semantic Kernel

Description du poste

Position Summary:

Avendata Group is actively seeking an experienced, high-caliber, and technical AI Full Stack Developer with 2 to 8 years of progressive professional experience in full-stack software engineering, .NET Core, Angular, and Generative AI applications to join our technology team on a full-time permanent remote basis in India (immediate joiners or candidates serving notice preferred). In this critical artificial intelligence engineering role, you will be responsible for designing, building, testing, and deploying production-grade AI products that integrate advanced Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) pipelines, and modern web frameworks. You will leverage your deep specialist expertise in C#, .NET Core, TypeScript, Angular, RESTful APIs, and vector databases to deliver uncompromised application performance, high scalability, and operational excellence. This opportunity offers competitive compensation, executive technical visibility, and exceptional career growth prospects within a premier global enterprise technology solutions and AI software development enterprise.

Detailed Job Description:

As an AI Full Stack Developer supporting Avendata Group on a remote basis in India, you will take full operational, tactical, and technical ownership of full-stack software development, generative AI integration, prompt engineering, and microservices architecture. Your day-to-day responsibilities include designing, developing, testing, and maintaining responsive web applications and AI-driven features utilizing Angular, TypeScript, .NET Core, and C#, building and optimizing end-to-end Retrieval-Augmented Generation (RAG) pipelines, integrating state-of-the-art Large Language Models (LLMs) and Generative AI services into enterprise workflows, leveraging advanced development tooling such as Cursor AI to accelerate feature delivery and code quality, architecting and maintaining secure REST APIs and distributed microservices architectures, interacting with vector databases and embedding stores (LlamaIndex, LangChain, Semantic Kernel) for context-aware AI search, conducting rigorous unit testing, code reviews, and performance tuning to ensure optimal user experience and low inference latency, collaborating closely with cross-functional data scientists, AI engineers, product owners, and QA squads in Agile environments, preparing comprehensive technical documentation of application architecture, API endpoints, and AI pipeline schemas, and ensuring strict adherence to enterprise security baselines, coding standards, and project delivery timelines. You will utilize your proactive troubleshooting and analytical problem-solving skills to resolve complex full-stack and AI pipeline anomalies under strict project schedules.

Key Responsibilities:

• Design, develop, test, and deploy production-ready full-stack web applications utilizing Angular and TypeScript for front-end architecture.
• Architect and maintain robust back-end microservices, REST APIs, and business logic using .NET Core and C#.
• Build, optimize, and scale advanced Retrieval-Augmented Generation (RAG) pipelines and Large Language Model (LLM) integration workflows.
• Leverage advanced AI-assisted development tools and coding environments like Cursor AI to accelerate software delivery.
• Integrate vector databases, embedding models, and orchestration frameworks including LlamaIndex, LangChain, and Semantic Kernel.
• Conduct rigorous unit testing, debugging, code refactoring, and performance profiling across full-stack components.
• Collaborate seamlessly with cross-functional AI engineers, data scientists, product managers, and QA squads in Agile sprint cycles.
• Ensure strict compliance with software engineering best practices, data security protocols, and enterprise coding standards.

Required Qualifications & Skills:

• Bachelor’s degree in Computer Science, Information Technology, Software Engineering, Artificial Intelligence, or a related technical discipline.
• Minimum of 2 to 8 years of progressive professional experience in full-stack software engineering and enterprise web application development.
• Strong, demonstrable hands-on professional expertise in .NET Core, C#, object-oriented programming, and backend service development.
• Comprehensive working knowledge of Angular, TypeScript, HTML5, CSS3, and modern front-end application development.
• Practical professional experience developing and deploying AI/LLM applications, Generative AI models, and RAG architectures.
• Solid practical proficiency in designing, consuming, and securing RESTful APIs and distributed microservices architectures.
• Hands-on experience utilizing modern AI coding assistants and development environments such as Cursor AI.
• Exceptional analytical, troubleshooting, debugging, and problem-solving capabilities under high-pressure enterprise conditions.
• Excellent written and verbal English communication skills with strong teamwork and stakeholder collaboration abilities.
• Mandatory legal work eligibility and physical availability for remote professional operations in India (Immediate joiners or notice period servers preferred).

Nice-to-Have Skills:

• Advanced professional certifications in Microsoft Azure .NET developer tracks, AWS, or AI/ML engineering domains.
• Prior professional working experience in top-tier AI product startups, enterprise software houses, or digital consulting firms.
• Hands-on familiarity with vector databases (Pinecone, Milvus, Chroma) and advanced orchestration frameworks (LlamaIndex, LangChain).
• Experience utilizing version control systems (Git), CI/CD deployment pipelines, and containerization platforms (Docker, Kubernetes).
• Exposure to prompt engineering, model fine-tuning, and semantic search optimization techniques.