Junior Generative AI engineer

Role & responsibilities We are looking for an experienced GenAI Developer to join our team and drive innovation in AI-driven applications. The ideal candidate will work with large language models (LLMs), agentic AI, retrieval-augmented generation (RAG), vector databases, and API development to build intelligent and scalable AI-powered solutions. Develop, fine-tune, and deploy LLM-based applications to enhance AI-driven capabilities. Implement Agentic AI workflows for autonomous decision-making and task execution. Design and optimize RAG pipelines to improve contextual retrieval and knowledge grounding. Work with vector databases (e.g., FAISS, Pinecone, Weaviate, pgvector) for efficient data retrieval and embedding storage. Build and integrate RESTful APIs using FastAPI or similar frameworks to enable seamless AI interactions. Optimize AI models for latency, efficiency, and cost-effectiveness in production environments. Integrate multimodal AI capabilities to process and generate content from various media formats. Embed real-time monitoring and analytics to generate insights and proactive recommendations. Ensure security, privacy, and ethical AI practices in all deployments. Preferred candidate profile Experience with LLMs (OpenAI, Anthropic, LLaMA, Mistral, etc.). Hands-on experience in Agentic AI frameworks (LangChain, AutoGPT, CrewAI, Agno (Phidata), etc.). Proficiency in RAG techniques for enhanced AI responses. Expertise in vector databases such as FAISS, Pinecone, ChromaDB, Weaviate, or pgvector. Strong Python programming skills with experience in FastAPI. Knowledge of embedding models (e.g., OpenAI embeddings, Hugging Face, BGE, etc.). Strong understanding of RESTful API integration and development. Perks and benefits