GenAI Engineer

As a GenAI Engineer (Senior/Lead) with 10 years of experience, you will be responsible for integrating LLM APIs, developing AI-driven applications, optimizing model performance, and deploying AI services at scale. Your expertise in Python-based AI development, LLM orchestration, cloud deployment, and enterprise AI integration will be crucial for this role. Your key responsibilities will include building and maintaining Python-based AI services using LangChain and CrewAI, implementing RAG-based retrieval and Agentic AI workflows. You will also be involved in integrating OpenAI, Bard, Claude, Azure OpenAI APIs, optimizing API calls, and reducing hallucinations using embedding-based retrieval methods like FAISS and Pinecone. Additionally, you will evaluate AI models, fine-tune embeddings, and enhance similarity search for retrieval-augmented applications. Designing scalable RESTful API services, securing AI endpoints using OAuth2, JWT authentication, and API rate limiting will also be part of your role. You will deploy AI-powered applications using AWS Lambda, Kubernetes, Docker, CI/CD pipelines, and implement LangChain for AI workflow automation. Working in Scrum teams, estimating tasks accurately, and contributing to incremental AI feature releases will be essential for Agile development and innovation. Your tech stack will include AI/ML tools such as PyTorch, TensorFlow, Hugging Face, Pinecone, LLMs & APIs like OpenAI, LangChain, CrewAI, cloud & DevOps tools such as AWS, Azure, Kubernetes, Docker, CI/CD, and security & compliance measures like OAuth2, JWT, and HIPAA. To excel in this role, you should have a minimum of 4 years of experience in AI/ML, LLM integrations, and enterprise cloud solutions, along with proven expertise in GenAI API orchestration, prompt engineering, and embedding retrieval. Strong knowledge of scalable AI architectures and security best practices will be highly beneficial.,