Job Description
We are seeking experienced AI Engineers / Agentic AI Developers to design, develop, and deploy enterprise-grade AI solutions with a focus on Agentic AI, Large Language Models (LLMs), and Retrieval-Augmented Generation (RAG). The successful candidate will be responsible for building intelligent AI agents and workflows capable of reasoning, planning, task execution, and orchestration while ensuring all solutions are deployed in an on-premises environment using local AI models and tools.
Key Responsibilities
- Gather, analyze, and translate business requirements into scalable AI and Agentic AI solutions.
- Design, develop, test, deploy, and maintain AI-powered applications and autonomous AI agents.
- Build Agentic AI workflows capable of reasoning, planning, task execution, and orchestration.
- Develop and integrate Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and multi-agent architectures.
- Integrate AI solutions with enterprise applications, APIs, databases, cloud services, and on-premises systems.
- Optimize AI models, prompts, workflows, and application performance.
- Ensure AI solutions comply with enterprise security, governance, privacy, and Responsible AI standards.
- Prepare technical documentation, deployment guides, operational manuals, and knowledge transfer materials.
- Provide technical support, troubleshooting, performance tuning, and continuous improvements.
- Design and implement AI solutions using on-premises infrastructure, local models, and enterprise-approved AI tools.
Requirements
- Bachelor's degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field.
- 5+ years of software development experience, including 2+ years working with AI/Generative AI technologies.
- Strong experience with Python and AI application development.
- Hands-on experience with Large Language Models (LLMs) and prompt engineering.
- Experience designing and implementing Retrieval-Augmented Generation (RAG) solutions.
- Experience building Agentic AI or multi-agent systems.
- Experience integrating AI applications with REST APIs, databases, and enterprise applications.
- Familiarity with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar.
- Experience working with vector databases such as Milvus, ChromaDB, FAISS, Pinecone, or equivalent.
- Knowledge of model deployment using Ollama, vLLM, Hugging Face Transformers, NVIDIA NIM, or similar on-premises inference platforms.
- Experience deploying and managing AI solutions in on-premises environments.
- Understanding of AI security, governance, privacy, and Responsible AI principles.
- Experience with Docker, Kubernetes, Git, and CI/CD pipelines is preferred.
- Strong analytical, problem-solving, communication, and documentation skills.
Preferred Skills
- Experience with open-source LLMs such as Llama, Mistral, Qwen, Gemma, or DeepSeek.
- Experience with GPU infrastructure and AI model optimization.
- Knowledge of MLOps practices and AI monitoring.
- Experience integrating AI solutions with enterprise platforms such as SAP, ServiceNow, Microsoft 365, or other enterprise systems.
- Experience working in highly secure or regulated enterprise environments.
This JD is aligned with your requirement that all AI use cases must run on-premises using local models and on-premises tools, making it suitable for enterprise or government projects.