DHI Solutions - Generative AI Engineer - RAG Framework

Experience Required

Job Summary

Key Responsibilities

• Design, develop, and optimize RAG pipelines using frameworks such as LangChain, LlamaIndex, or custom built stacks.
• Implement Agentic AI architectures involving task-based agents, stateful memory, planning-execution workflows, and tool augmentation.
• Perform model fine-tuning, embedding generation, and evaluation of LLM outputs; incorporate human and automated feedback loops.
• Build and enforce guardrails to ensure safe, compliant, and robust model behaviorincluding prompt validation, output moderation, and access controls.
• Collaborate with cross-functional teams to deploy solutions in cloud-native environments such as Azure OpenAI, AWS Bedrock, or Google Vertex AI.
• Contribute to system observability via dashboards and logging, and support post-deployment model monitoring and optimization.
  

Required Qualifications

• Proven production experience with RAG frameworks like LangChain, LlamaIndex, or custom-built solutions
• Solid understanding of Agentic AI design patterns: task agents, memory/state tracking, and orchestration logic
• Strong expertise in LLM fine-tuning, vector embeddings, evaluation strategies, and feedback integration
• Experience with implementing AI guardrails (e.g., moderation, filtering, prompt validation)
• Proficiency in Python, LLM APIs (OpenAI, Anthropic, Cohere, etc.), and vector database integration
• Familiarity with CI/CD pipelines, API integrations, and cloud-native deployment patterns
  

Preferred Qualifications

• Experience working on AI projects in regulated environments (Banking domain)
• Hands-on experience with cloud AI platforms : Azure OpenAI, AWS Bedrock, or Google Vertex AI
• Knowledge of prompt engineering, RLHF, and LLM observability frameworks
• Experience building or leveraging internal LLM evaluation harnesses, agent orchestration layers, or compliance dashboards