Senior AI Engineer

At PwC, our people in data and analytics engineering focus on leveraging advanced technologies and techniques to design and develop robust data solutions for clients. They play a crucial role in transforming raw data into actionable insights, enabling informed decision-making and driving business growth.

Those in intelligent automation at PwC will focus on conducting process mining, designing next generation small- and large-scale automation solutions, and implementing intelligent process automation, robotic process automation and digital workflow solutions to help clients achieve operational efficiencies and reduce costs.

Job Summary:

We are seeking a passionate and skilled AI Engineer with 3-7 years of experience, including a minimum of 2 years in Generative AI (GenAI), to join our AI/ML team. The AI Engineer will play a key role in building and deploying advanced AI solutions leveraging Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), multi-agent frameworks, and state-of-the-art tooling.

Responsibilities:

• Design, develop, and deploy GenAI solutions, with a focus on real-world production readiness.
• Build and scale Retrieval-Augmented Generation (RAG) systems for enterprise use cases.
• Integrate with graph-based memory and tool-using agents to enhance LLM capabilities.
• Implement multi-agent orchestration and reasoning systems (e.g., AutoGen, LangGraph, custom agents).
• Use LLM frameworks and libraries (e.g., LangChain, AutoGen, LangGraph, etc.).
• Write clean, efficient, and scalable code in Python (or other languages as needed).
• Collaborate across cross-functional teams to translate business needs into scalable GenAI-powered systems.
• Ensure system scalability, reliability, and maintainability through strong software engineering practices.

Mandatory skill sets:

• 3-7 years of total experience in AI/ML or software engineering.
• Minimum 2 years of hands-on experience in building and deploying GenAI systems.
• Experience in working with LLMs such as GPT-4, Claude 2/Gemini, etc.
• Strong hands-on knowledge of RAG systems and multi-agent frameworks like LangGraph, LangChain, or AutoGen.
• Proficiency in Python and familiarity with cloud-native deployments (e.g., APIs, containers, microservices).
• Solid understanding of software engineering best practices, including version control, testing, and CI/CD.
• Experience in working with graph-based memory and LLM tool use patterns.

Preferred skill sets:

• Experience with tool-using agents, memory-augmented architectures, or cognitive architectures.
• Prior contributions to open-source GenAI or agent frameworks.
• Familiarity with Azure OpenAI, AWS Bedrock, or other cloud-based LLM services.
• Background in optimization, evaluation, and prompt engineering for LLM systems.
• Experience in deploying AI systems in production environments and maintaining performance at scale.

Education qualification:

Bachelor's degree in Computer Science, Engineering, or a related field.

Education:

Degrees/Field of Study required: Master of Engineering, Bachelor of Engineering