Senior Agentic Pipeline 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.

We are looking for an experienced Agentic Pipeline Engineer to design, develop, and operationalize AI-driven pipelines and agentic workflows. The ideal candidate will have strong hands-on experience in Python, Generative AI, LLM applications, agent frameworks, APIs, and cloud-based AI solutions, along with a good understanding of production-grade software engineering practices.

The role involves building intelligent multi-step workflows where AI agents can reason, interact with enterprise systems, use tools/APIs, retrieve relevant information, and execute tasks reliably.

Responsibilities:

• Design and develop Agentic AI pipelines and workflows using Large Language Models (LLMs).
• Build single-agent and multi-agent solutions for complex business use cases.
• Develop reusable components for tool calling, orchestration, prompt management, memory, routing, and workflow execution.
• Implement RAG (Retrieval-Augmented Generation) pipelines integrating enterprise data sources with LLM applications.
• Integrate agents with REST APIs, databases, vector stores, enterprise applications, and external tools.
• Build scalable backend services and APIs using Python and frameworks such as FastAPI.
• Work with agentic frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, or equivalent frameworks.
• Develop and optimize embedding, retrieval, chunking, reranking, and vector-search pipelines.
• Implement appropriate guardrails, validation, error handling, observability, logging, and evaluation for GenAI applications.
• Optimize agent workflows for accuracy, latency, reliability, and cost.
• Containerize and deploy AI services using Docker and CI/CD practices.
• Collaborate with architects, engineering teams, data scientists, and business stakeholders to translate use cases into production-ready Agentic AI solutions.
• Perform unit testing, integration testing, troubleshooting, and production support for AI pipelines.

Mandatory skill sets:

• 3-7 years of software engineering / AI engineering experience.
• Strong programming experience in Python.
• Hands-on understanding of Generative AI and Large Language Models.
• Experience developing LLM-based applications and agentic workflows.
• Strong understanding of RAG architecture and vector-based retrieval.
• Experience with Vector Databases / Search, such as FAISS, Pinecone, Weaviate, Chroma, Azure AI Search, or equivalent.
• Experience integrating REST APIs, databases, and enterprise applications.
• Knowledge of prompt engineering, tool/function calling, structured outputs, embeddings, and context management.

Preferred skill sets:

• Knowledge of frameworks such as:
• LangGraph
• Microsoft Semantic Kernel
• AutoGen or similar agent frameworks
• Experience with Git, Docker, CI/CD, and API development.
• Exposure to at least one major cloud platform such as Azure, AWS, or GCP.

Education qualification:

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