Revalsys Technologies - Full Stack Engineer - AI/LLM Integration

Description :

Full Stack Engineer R&D (LLM & AI Solutions)

Job Description :

We are looking for a passionate and skilled Full Stack Engineer with strong experience in Research & Development (R&D) and Large Language Models (LLMs). The ideal candidate will have around 3 years of experience in building scalable applications and working on AI-driven solutions such as chatbots, RAG systems, and vector-based search.

Key Responsibilities :

- Design, develop, and maintain full-stack applications with a focus on AI/LLM integration

- Implement and optimize LLM-based solutions (OpenAI, Hugging Face, etc.)

- Build and deploy RAG (Retrieval-Augmented Generation) pipelines

- Work with vector databases (Pinecone, FAISS, Weaviate, etc.)

- Develop backend services and APIs using technologies like .NET, Java

- Build responsive frontend applications using Angular

- Collaborate with R&D teams to prototype and innovate new AI solutions

- Optimize performance, scalability, and security of applications

- Stay updated with the latest advancements in AI/ML and LLM ecosystems

Required Skills :

- 3+ years of experience in Full Stack Development

- Strong experience with LLMs and AI tools

- Hands-on experience in RAG implementation

- Experience with vector databases and embeddings

- Proficiency in backend technologies: .NET / Java

- Frontend experience with Angular

- Knowledge of REST APIs, Microservices architecture

- Familiarity with cloud platforms (Azure/AWS is a plus)

- Strong problem-solving and analytical skills

Good to Have :

- Experience with LangChain/LlamaIndex

- Knowledge of prompt engineering

- Experience in chatbot development

- Exposure to DevOps and CI/CD pipelines

Experience :

- 3+ Years