Data Scientist

As a Data Scientist you will:

• Build intelligent, end-to-end data pipelines that utilize large language models (LLMs) for document generation, summarization, reasoning, and automating tasks.

• Design and develop autonomous workflows where AI agents interact with tools, APIs, memory, and other agents to accomplish complex, multi-step objectives.

• Apply prompt engineering, retrieval-augmented generation (RAG), and planning techniques to enable contextual reasoning and decision-making in LLM-powered systems.

• Analyze legacy systems such as rule-based engines, stored procedures, and monolithic applications, and convert them into modular, AI-native components that work with structured and unstructured data.

• Fine-tune foundation models or adapt them using low-rank adaptation (LoRA), transfer learning, or domain-specific techniques for enhanced task performance.

Skills Required:

•  5+ years of experience in AI/ML development, with a strong emphasis on LLM integration and intelligent system design.
•  Proven experience in designing, developing and deploying real-world LLM-based applications and agentic systems.
•  Expert-level knowledge of Python for building and orchestrating machine learning and AI applications, with a focus on LLM-based development.
•  Proficiency in prompt engineering, chaining logic, context window management, and invoking tools (e.g., APIs, functions) within LLM applications.
•  Understanding of agent patterns involving memory, planning, multi-agent coordination, and decision-making frameworks.
•  Experience with vector databases, embedding generation, and retrieval-augmented generation (RAG) for knowledge-based AI systems.
•  Hands-on experience deploying and managing AI services in cloud platforms, preferably Microsoft Azure.