About this role
Job Description & Summary
The opportunity
Provide hands-on engineering leadership for agentic AI products, define implementation patterns and ensure technical quality from prototype through production.
What you will be doing
· Lead technical design and implementation of agents, RAG services, tool integrations and model orchestration. · Establish coding, testing, evaluation, review and documentation standards. · Decompose architecture into engineering work and guide estimation and sprint planning. · Coach engineers, review code and resolve complex technical problems. · Design evaluation suites for quality, safety, reliability, latency and cost. · Work with architects and MLOps to harden solutions for production.
What we need from you
· 6+ years in software, data or machine-learning engineering, including hands-on AI delivery. · Strong Python and API engineering capability and experience with modern agent or LLM frameworks. · Experience with retrieval, embeddings, vector stores, model evaluation and distributed systems. · Ability to lead agile engineering teams while remaining hands-on.
Relevant AI technologies and tooling · Strong hands-on expertise in Python and API engineering, with production experience using agent frameworks such as LangChain and LangGraph, Microsoft Agent Framework or Semantic Kernel, OpenAI Agents SDK, AutoGen, CrewAI, or equivalent. · Ability to implement graph-based and code-first orchestration patterns, including state, memory, checkpoints, tool calling, hand-offs, retries, idempotency, human approval and long-running workflows. · Advanced experience with RAG, structured outputs, prompt and context engineering, embeddings, vector or hybrid retrieval, reranking, knowledge graphs and retrieval evaluation. · Experience integrating agents with enterprise systems through REST or GraphQL APIs, events, queues, databases and MCP-compatible tools or servers. · Practical experience with automated evaluation and observability using technologies such as LangSmith, MLflow, Langfuse, OpenTelemetry, Azure AI evaluation capabilities or equivalent, covering quality, trajectory, latency, token use and cost. · Strong software-engineering discipline across pytest or equivalent testing, type checking, code review, dependency management, secure coding, CI/CD and containerized deployment.
Measures of success · Engineering throughput and predictability · Code quality and automated test coverage · Evaluation performance and production readiness · Reduction of defects and rework · Development of reusable components
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