AI Engineer (LLM / Agentic Systems)

Key Responsibilities

• Design, develop, and deploy AI-powered applications using LLMs

• Build and maintain RAG (Retrieval-Augmented Generation) pipelines with vector databases

• Develop agentic workflows using frameworks like LangChain and LangGraph

• Implement multi-agent orchestration systems for complex workflows

• Develop and optimize Text-to-SQL agents for structured data querying

• Enable real-time / streaming AI responses for interactive applications

• Integrate AI solutions with APIs, backend services, and front-end applications

• Deploy and manage AI services using Azure DevOps pipelines

Required Skills & Qualifications

• Strong programming skills in Python (mandatory)

• Hands-on experience with:

  • LangChain, LangGraph, or similar LLM frameworks

  • Agent-based architectures and orchestration

  • Vector databases (e.g., Pinecone, FAISS, Weaviate)

• Experience building and optimizing RAG pipelines

• Understanding of prompt engineering and prompt optimization techniques

• Experience working with LLM APIs (e.g., OpenAI API, Azure OpenAI Service)

• Knowledge of Text2SQL, semantic search, and embeddings

• Experience implementing streaming responses (SSE/WebSockets)

Additional Requirements (Recommended)

• Understanding of multi-agent systems design patterns

• Experience with LLM evaluation frameworks (e.g., RAG evaluation, hallucination detection)

• Familiarity with fine-tuning / model adaptation (LoRA, adapters)

• Experience with document processing pipelines (PDF, OCR, chunking strategies)

• Knowledge of data pipelines and ETL processes

• Familiarity with Docker and containerized deployments

• Experience with cloud platforms (especially Azure)

• Understanding of CI/CD pipelines and DevOps practices

• Experience with monitoring & observability for AI systems (latency, token usage, cost tracking)