Dutech’s Job

We are seeking a highly skilled Senior AI Engineer to design, build, and deploy production-grade AI systems powered by Large Language Models (LLMs). This role focuses on developing autonomous agents, multi-agent systems, and Retrieval-Augmented Generation (RAG) architectures.

The ideal candidate will have hands-on experience with frameworks like LangChain, LangGraph, CrewAI, or AutoGPT, strong Python expertise, and a deep understanding of context engineering, AI governance, and scalable enterprise AI solutions.

Key Responsibilities

• Design and deploy production-ready autonomous AI agents and agentic workflows.
• Build and optimize RAG architectures using vector databases.
• Develop solutions using LLM frameworks such as LangChain, LangGraph, CrewAI, or AutoGPT.
• Integrate LLMs via APIs (OpenAI, Hugging Face, Azure AI) into enterprise applications.
• Implement and extend the Model Context Protocol (MCP) for secure and standardized data access.
• Apply context engineering techniques to improve model performance and response quality.
• Implement AI guardrails, content filtering, and safety mechanisms.
• Ensure compliance with data privacy standards, including handling of PII and PHI.
• Collaborate with cross-functional teams to design scalable enterprise AI architectures.
• Optimize LLM performance, token usage, and cost efficiency.
• Contribute to AI governance, model lifecycle management, and evaluation frameworks.

Required Qualifications

• 4+ years of experience in AI/ML engineering or advanced data science.
• Proven experience building and deploying production-grade autonomous agents.
• Strong expertise in context engineering and prompt design strategies.
• Hands-on experience with LangChain, LangGraph, CrewAI, AutoGPT, or similar frameworks.
• Experience implementing RAG architectures with vector databases.
• Proficiency in Python and AI/ML libraries (OpenAI, Hugging Face, Azure AI).
• Experience integrating LLMs via APIs into real-world applications.
• Knowledge of AI governance, model lifecycle management, and evaluation.
• Experience implementing AI safety controls, guardrails, and content filtering.
• Understanding of data privacy and secure handling of sensitive data (PII/PHI).

Preferred Qualifications

• Experience building multi-agent or agentic AI workflows.
• Experience optimizing LLM cost, latency, and token usage.
• Familiarity with enterprise AI deployment patterns and scalability.
• Exposure to secure AI architectures and compliance frameworks.