AI Engineer (GenAI – Vertex AI & GCP)

Nexamind is looking for a motivated AI Engineer with hands-on experience in Generative AI solutions on Google Cloud Platform (GCP). The ideal candidate will have practical exposure to Vertex AI, LLM integrations, Vector Databases, embeddings, and token optimization, and will contribute to building scalable AI-powered applications.

Key Responsibilities

• Design and develop Generative AI applications using Vertex AI on GCP.
• Build and deploy LLM-powered use cases such as chatbots, summarization, and document intelligence.
• Implement Retrieval-Augmented Generation (RAG) pipelines using Vector Databases and embeddings.
• Manage token usage, prompt engineering, and context optimization for LLM applications.
• Develop backend services and APIs to integrate AI capabilities into products.
• Fine-tune and evaluate foundation models where required.
• Monitor, optimize, and scale AI workloads on GCP.
• Collaborate with data scientists, product teams, and DevOps for production deployment.
• Ensure performance, reliability, and security of AI solutions.

Required Skills

• 2+ years of hands-on experience in AI/GenAI development.
• Strong experience with Google Cloud Platform (GCP) and Vertex AI.
• Practical knowledge of LLM concepts, embeddings, tokens, and Vector Databases.
• Experience building RAG-based or LLM-powered applications.
• Proficiency in Python and backend development.
• Experience with REST APIs and microservices.
• Understanding of prompt engineering and LLM evaluation.
• Familiarity with Git and CI/CD workflows.

Preferred Qualifications

• Experience with Gemini or other modern LLMs.
• Exposure to LangChain, LlamaIndex, or similar frameworks.
• Knowledge of MLOps practices on GCP.
• Experience deploying AI solutions in production environments.
• Good communication and problem-solving skills.