Generative AI Engineer

### Generative AI Engineer

ContractC2C Los Angeles, CA / Remote Visa: US CitizenGreen CardGC-EADH1BH4-EADOPTEADTN Job Summary: We are seeking a Generative AI Engineer to design, develop, and deploy production-grade GenAI applications for entertainment, content, and customer-care use cases. The ideal candidate will have strong Python and software engineering expertise, hands-on experience with LLMs and RAG architectures, and a proven ability to build scalable AI solutions in production environments. Work Experience: 5–7 Years Responsibilities Build, test, deploy, and maintain production-ready GenAI applications using Python, LangChain, LlamaIndex, and microservices architectures. Design and implement high-accuracy Retrieval-Augmented Generation (RAG) pipelines for content metadata, sports statistics, knowledge bases, and related use cases. Integrate LLM capabilities into client applications across Gemini OS, iOS, Android, and Smart TV platforms using RESTful APIs and WebSockets. Develop scalable, reliable, and maintainable AI services aligned with production engineering best practices. Fine-tune open-source LLMs such as Llama and Mistral using LoRA/QLoRA for specialized entertainment and customer-care applications. Build automated evaluation frameworks using tools such as Ragas and TruLens. Measure and optimize model performance across hallucination rate, latency, relevance, response accuracy, and overall user experience. Analyze model behavior and continuously improve quality through data, prompt, and model optimization. Develop, optimize, test, and version-control complex prompts and agentic workflows. Design multi-step LLM orchestration workflows for reliable task execution and intelligent decision-making. Implement fallback mechanisms, circuit breakers, and AI safety controls to improve system resilience. Use frameworks such as NeMo Guardrails and Guardrails AI to establish safe and reliable user interactions. Partner with MLOps,