Job Description & Summary

The opportunity

Build, test and integrate production-grade AI agents and services that execute business tasks reliably within enterprise workflows.

What you will be doing

·        Implement agents, prompts, tools, retrieval pipelines and orchestration logic.

·        Integrate AI components with enterprise APIs, applications, databases and workflow services.

·        Build automated tests and evaluation datasets for functional and non-functional behavior.

·        Diagnose model, retrieval, tool-use and integration failures.

·        Contribute to secure coding, documentation, peer review and release activities.

·        Participate actively in agile ceremonies, demonstrations and backlog refinement.

What we need from you

·        3+ years in software, data or AI engineering.

·        Strong Python or comparable programming skills, API development and version control.

·        Practical experience with LLM applications, RAG, agents, embeddings and structured outputs.

·        Ability to work iteratively with product, architecture, data and user-experience specialists.

Relevant AI technologies and tooling

·        Hands-on experience building agents with at least one production-oriented framework such as LangChain and LangGraph, Microsoft Agent Framework or Semantic Kernel, OpenAI Agents SDK, AutoGen, CrewAI, or equivalent.

·        Strong Python skills and practical experience with FastAPI or similar API frameworks, Pydantic or comparable schema validation, asynchronous programming, Git and automated testing.

·        Practical experience implementing tool calling, structured outputs, agent state and memory, hand-offs, guardrails, retries, human-in-the-loop steps and deterministic workflow nodes.

·        Experience implementing RAG pipelines using embeddings, vector or hybrid search, metadata filters, reranking and evaluation datasets.

·        Familiarity with MCP, enterprise API integration, queues or events, containerization with Docker and deployment to Kubernetes or managed application platforms.

·        Ability to instrument agent executions using tracing and evaluation tools such as LangSmith, MLflow, Langfuse, OpenTelemetry or platform-native equivalents.

Measures of success

·        Working features delivered per iteration

·        Evaluation results and defect rates

·        Integration reliability

·        Code review and documentation quality

·        Contribution to reusable engineering assets

Key interfaces

·        Other members of the AI Transformation & Agentic Systems Practice

·        PwC sector, functional, cloud, cyber, risk, Responsible AI and change specialists

·        Client business owners, product owners, technology teams and operational users

·        Technology alliance and implementation partners where relevant

Contribution to the practice

·        Support proposals, client workshops and market development appropriate to seniority.

·        Contribute reusable methods, patterns, code, assets and lessons learned.

·        Coach colleagues and participate in the capability’s continuous learning agenda.

·        Uphold PwC quality, independence, confidentiality and risk-management requirements.

#LI-BS1 #LI-Hybrid