Global IT Combine - Artificial Intelligence Engineer - LLM Models

Description :

- Design, build, and deploy LLM-based applications using Python and Azure OpenAI Services.

- Develop Retrieval-Augmented Generation (RAG) pipelines with vector databases like Azure Cognitive Search, Pinecone, or FAISS.

- Create intelligent agents using frameworks such as LangChain, LlamaIndex, or Semantic Kernel.

- Apply advanced prompting techniques, including:

- Chain-of-Thought (CoT).

- Tree-of-Thoughts (ToT).

- ReAct, Self-Consistency, and Toolformer-style prompting.

- Implement reasoning strategies for multi-step decision-making and task decomposition.

- Orchestrate agentic AI workflows, integrating external tools, APIs, and business logic.

- Deploy scalable LLM services with Azure Functions, Docker, and serverless architectures.

- Monitor and optimize model performance, latency, and reliability.

Must-Have Skills :

- Proven integration of Azure OpenAI (GPT models) into real-world applications.

- Strong understanding of LLMs, embeddings, vector search, and RAG architectures.

- Experience with at least one LLM orchestration framework: LangChain, LlamaIndex, or Semantic Kernel.

- Knowledge of structured prompting techniques and LLM reasoning models.

- Ability to integrate external APIs, cloud tools, and business data into LLM pipelines.

- Familiarity with Azure Functions, Docker, and cloud-native development.

- Excellent debugging and performance optimization skills.

Good-to-Have Skills :

- Background in building AI developer tools, automation bots, or assistants.

- Exposure to LLMOps practices: versioning, prompt evaluation, monitoring.

- Familiarity with traditional NLP tasks: summarization, classification, Q&A.

- Experimental prompting experience: role prompting, reflection-based refinement, zero-shot CoT, etc.