We are looking for a skilled Senior AI Developer to join our dynamic team. The ideal candidate will have expertise in developing and deploying AI-driven applications with a focus on retrieval-augmented generation (RAG), conversational RAG (CRAG), LangChain, LangFlow, and LanceDB. You will be responsible for designing, building, and optimizing AI models and pipelines, ensuring scalable and efficient deployment using FastAPI, Kubernetes (K8s), and Docker. As a Senior AI Developer, your responsibilities will include developing and implementing AI solutions leveraging LangChain, LangFlow, and LanceDB. You will design and optimize retrieval-augmented generation (RAG) and conversational RAG (CRAG) pipelines, as well as build and deploy AI-driven applications using FastAPI for scalable and high-performance APIs. Containerizing applications using Docker and orchestrating deployments on Kubernetes (K8s) will also be part of your role. Additionally, you will integrate AI models with databases and vector stores to enhance search and retrieval capabilities. Collaborating with cross-functional teams to design and implement end-to-end AI solutions, ensuring code quality, scalability, and security of AI applications, and staying updated with the latest advancements in AI, ML, and NLP technologies are essential aspects of this position. The qualifications we are looking for include proficiency in LangChain and LangFlow, experience working with LanceDB or other vector databases, a strong understanding of RAG and CRAG methodologies, hands-on experience with FastAPI, expertise in containerization with Docker and orchestration with Kubernetes (K8s), experience in designing and deploying scalable AI solutions, proficiency in Python and relevant AI/ML frameworks, strong problem-solving skills, ability to work in an agile development environment, familiarity with cloud platforms (AWS, GCP, Azure), experience with FAISS, Pinecone, Weaviate, or other vector stores, knowledge of OpenAI, Hugging Face Transformers, LlamaIndex, or fine-tuning LLMs, familiarity with SupaBase and Jenkins, and understanding of API gateway and load balancer. Preferred qualifications include experience in deploying AI solutions in a production environment, knowledge of MLOps tools like MLflow, Kubeflow, or Airflow for managing AI pipelines, understanding of model fine-tuning and optimization techniques, experience with monitoring and maintaining AI applications post-deployment, familiarity with AWS SageMaker, GCP Vertex AI, or Azure AI Services, and understanding of data privacy, model security, and ethical AI practices. Founded in 1986, Chiposoft is a leading software services firm based in New Delhi, India, focused on AI powered solutions and products. With almost four decades of experience, we have built a reputation for technical excellence, deep business process understanding, and customer-centric solutions. Our expertise spans AI-driven solutions, enterprise applications, and digital platforms that empower organizations to streamline operations, enhance engagement, and drive innovation. At Chipsoft, we pride ourselves on delivering state of the art, reliable, and scalable solutions while maintaining a dynamic and collaborative work environment. Our growing team of skilled professionals thrives on innovation and problem-solving, working on cutting-edge technologies and global projects, including clients in India, the US, the UK, Middle East, and Africa. As we expand our reach and explore AI-powered solutions through strategic partnerships, we are looking for talented and passionate professionals to join our team. If you are eager to work on exciting projects, cutting-edge technologies, and make a real impact, we invite you to be part of our journey. Join us and shape the future of digital transformation!,