Generative AI Developer

<p><p><b>Description :</b><br/><br/>Role Summary :<br/><br/>We are seeking a highly skilled Gen AI Developer Specialist with extensive experience in building, deploying, and scaling production-grade Generative AI applications leveraging Large Language Models (LLMs), vector databases, and cloud AI platforms.<br/><br/>The ideal candidate will have hands-on expertise in implementing real-world AI solutions that solve complex business challenges while adhering to ethical AI practices.<br/><br/>You will lead the end-to-end design, development, and deployment of scalable GenAI systems, working closely with cross-functional teams to drive innovation and operational excellence.<br/><br/><b>Key Responsibilities :</b><br/><br/>- Architect and develop GenAI applications using state-of-the-art LLMs such as OpenAI GPT, Claude, LLaMA, and other transformer-based models.<br/><br/>- Build Retrieval-Augmented Generation (RAG) pipelines integrating vector search with knowledge bases.<br/><br/>- Implement multimodal AI use cases combining text, images, audio, and video data.<br/><br/>- Develop agent-based AI workflows for autonomous task execution and decision-making.<br/><br/>- Identify AI-driven business opportunities and design cost-effective AI solutions.<br/><br/>- Optimize model usage, API calls, and infrastructure costs without compromising performance.<br/><br/>- Apply responsible AI principles to ensure fairness, transparency, and ethical use.<br/><br/>- Implement safeguards against prompt injection, jailbreaking, and other security threats.<br/><br/>- Design Human-in-the-Loop (HITL) systems for supervised AI outputs and continuous improvement.<br/><br/>- Process and analyze real-time voice and text inputs, including chunking, parsing, and conversion for downstream AI models.<br/><br/>- Deploy and manage scalable GenAI applications on Azure AI Studio, AWS Bedrock, or similar cloud platforms.<br/><br/>- Work with DevOps and cloud engineering teams to implement CI/CD pipelines, monitoring, and automated scaling.<br/><br/>- Collaborate with data scientists, software engineers, product managers, and stakeholders to deliver AI-powered features.<br/><br/>- Mentor junior developers and promote best practices in GenAI development and deployment.<br/><br/><b>Required Skills & Experience :</b><br/><br/>- Proven experience with Azure OpenAI Service and/or AWS Bedrock platforms for AI application development.<br/><br/>- Strong expertise in Python programming, with frameworks such as FastAPI, LangChain, or equivalent for building AI-powered APIs and pipelines.<br/><br/>- Hands-on experience with vector databases like FAISS, Pinecone, or Weaviate for embedding-based search and retrieval.<br/><br/>- Deep understanding of Retrieval-Augmented Generation (RAG) techniques and implementation.<br/><br/>- Familiarity with prompt engineering and prompt safety best practices to secure AI models.<br/><br/>- Experience building and deploying production-grade AI applications with scalable architecture.<br/><br/>- Knowledge of responsible AI principles, bias mitigation, and AI ethics.<br/><br/>- Expertise in handling real-time data ingestion, chunking, and pre-processing for AI workflows.<br/><br/>- Strong problem-solving skills and ability to communicate complex AI concepts to technical and non-technical audiences<br/></p><br/></p> (ref:hirist.tech)