Description

Lead the design and development of scalable GenAI solutions, focusing on LLMs and Agentic AI.

This role is hybrid.

Responsibilities

• Architect end-to-end LLM solutions using Azure OpenAI, Azure AI Studio, and Hugging Face.
• Design and optimize RAG pipelines, including data ingestion, embedding generation, and vector search.
• Build goal-oriented autonomous agents capable of planning, task decomposition, and tool invocation.
• Implement fine-tuning and parameter-efficient tuning (LoRA, QLoRA, PEFT) with memory modules.
• Establish security guardrails and governance policies for LLM-based applications.

Required Skills

• 10+ years total experience in AI/ML roles, with 2-3 years in Generative AI applications.
• 5+ years building Python-based backend services, APIs, and orchestrators.
• Proficiency in LLM chaining, prompt engineering, and LangChain.
• Experience with multi-agent frameworks: LangChain, AutoGen, DSPy, or LangGraph.
• Strong background in Data Science and Machine Learning principles.
• Experience with vector search tools: Azure Cognitive Search, Pinecone, Weaviate, or FAISS.
• Knowledge of OpenAI APIs and Azure OpenAI model optimization.
• Bachelor's or Master's degree in Computer Science, Data Science, or related field.

Preferred Skills

• Experience with custom model integration and memory modules (LTM, STM, episodic memory).
• Proven track record providing technical strategy to customers.

Key Skills

Education

Bachelor's or Master's degrees