Dutech’s Job

We are seeking a highly skilled Senior Generative AI Engineer with deep expertise in Large Language Models (LLMs), autonomous agents, and Retrieval-Augmented Generation (RAG). The ideal candidate will have hands-on experience building and deploying production-grade AI systems using modern frameworks such as LangChain, LangGraph, CrewAI, or AutoGPT.

This role focuses on designing scalable, secure, and high-performance AI solutions for enterprise applications.

Key Responsibilities:

• Design, build, and deploy production-grade autonomous AI agents
• Develop and implement RAG architectures using vector databases
• Work with frameworks such as LangChain, LangGraph, CrewAI, and AutoGPT
• Integrate LLMs via APIs (OpenAI, Hugging Face, Azure AI)
• Apply context engineering techniques to improve LLM responses
• Develop and manage multi-agent systems and workflows
• Implement and extend Model Context Protocol (MCP) for secure data access
• Apply AI governance, model lifecycle management, and evaluation frameworks
• Implement AI guardrails, content filtering, and safety mechanisms
• Optimize LLM performance, cost, and token usage
• Ensure compliance with data privacy standards (PII/PHI handling)
• Collaborate with cross-functional teams to build scalable AI solutions

Required Qualifications:

• 4+ years of experience in AI/ML Engineering or Advanced Data Science
• Proven experience building autonomous AI agents in production environments
• Strong hands-on experience with LangChain, LangGraph, CrewAI, or AutoGPT
• Experience implementing RAG architectures with vector databases
• Proficiency in Python and AI/ML libraries (OpenAI, Hugging Face, Azure AI)
• Experience integrating LLMs via APIs
• Strong understanding of AI governance and model lifecycle management
• Experience with Model Context Protocol (MCP) or similar frameworks
• Knowledge of AI safety, guardrails, and content moderation
• Understanding of data privacy and sensitive data handling

Preferred Qualifications:

• Experience building multi-agent or agentic workflows
• Experience optimizing LLM performance, cost, and scalability
• Familiarity with enterprise AI deployment patterns