Role Overview We are looking for an AI Engineer to design, build, deploy, and scale production-grade LLM and Generative AI applications. The ideal candidate should have strong hands-on experience with Python, LLM APIs, RAG systems, vector databases, SQL, and modern AI application frameworks. This role is suited for engineers who have already worked on real-world GenAI applications beyond prototypes or basic API integrations. Key Responsibilities Build and deploy production-grade LLM and Generative AI applications Develop Retrieval-Augmented Generation (RAG) pipelines Work with embeddings, semantic search, reranking, and vector databases Integrate LLM APIs such as OpenAI, Gemini, Anthropic, or similar models Build AI agents with tool calling / function calling Develop agentic workflows using frameworks such as LangGraph, Pydantic AI, or similar Design prompts, structured outputs, evaluation pipelines, and guardrails Integrate LLM applications with databases, APIs, and internal systems Write and optimize SQL queries for data retrieval and AI workflows Improve LLM application accuracy, latency, reliability, and scalability Monitor and troubleshoot AI systems running in production Mandatory Skills 1+ years of relevant software / AI engineering experience Strong hands-on experience with Python Practical experience building applications using LLMs / Generative AI Strong understanding of RAG architecture Hands-on experience with embeddings and vector databases Experience working with OpenAI, Gemini, Anthropic, or comparable LLM APIs Experience with AI agents, tool calling, or function calling Hands-on knowledge of LangGraph, Pydantic AI, or similar agent frameworks Strong understanding of LLMs Strong hands-on experience with SQL LLM and SQL experience are mandatory for this role. Preferred Experience Production deployment of GenAI applications LLM evaluation and observability Prompt engineering and structured outputs FastAPI or similar backend frameworks Cloud deployment on AWS, GCP, or Azure Docker and API-based architectures Experience optimizing LLM cost, latency, and response quality Ideal Candidate You should be comfortable taking an AI use case from problem definition → architecture → development → deployment → production scaling. We are specifically looking for candidates with practical experience building real LLM-powered products, not only academic projects or basic chatbot implementations.

About Quickhyre AI

QuickHyre AI is an online job portal and HRMS software platform for hiring and workforce management, trusted by over 10 million active users. It connects freshers and experienced professionals across all career levels with verified job opportunities, while enabling companies to hire, onboard, and manage employees through a single system. Candidates use QuickHyre AI to search and apply for jobs across entry-level, mid-level, and senior roles, including internships and contract positions across tech and non-tech domains. Employers use QuickHyre AI as a hiring platform, applicant tracking system (ATS), and HRMS to post jobs, screen candidates, manage applications, onboard hires, and maintain employee records. Built for startups, growing companies, and enterprises, QuickHyre AI reduces irrelevant applications, improves hiring efficiency, and simplifies HR operations. By combining job discovery, online recruitment, and HR management software, QuickHyre AI supports end-to-end talent acquisition and workforce administration at scale.