Agentic AI Developer
PwC is seeking an experienced Agentic AI Developer to design, build, and deploy intelligent autonomous agent systems using Python. In this role, you will architect multi-agent workflows, integrate LLMs with real-world tools, and develop orchestration layers for self-directed AI pipelines. This position combines AI engineering, backend development, and system design. As part of our team, you will use advanced technologies to transform data into actionable insights for clients, driving business growth and operational efficiency.
Job description
Job Description & Summary
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.
Responsibilities
- Design and develop autonomous and semi-autonomous AI agents capable of multi-step reasoning, planning, and decision-making
- Build multi-agent systems with defined roles, inter-agent communication, and collaborative task execution
- Implement agent orchestration frameworks (LangGraph, AutoGen, CrewAI, or custom-built) for workflow coordination
- Define and manage agent memory layers - short-term (context window), long-term (vector stores), and episodic memory
- Develop tool-use and function-calling pipelines enabling agents to interact with APIs, databases, and external services
- Integrate and fine-tune interactions with LLM providers (OpenAI, Anthropic, Mistral, open-source models via HuggingFace)
- Design robust prompt templates, system instructions, and chain-of-thought strategies for reliable agent behavior
- Implement RAG (Retrieval-Augmented Generation) pipelines connecting agents to structured and unstructured knowledge bases
- Build FastAPI-based microservices to expose agent capabilities as REST/streaming APIs
- Develop event-driven agent triggers using message queues (Redis Streams, Kafka, RabbitMQ)
- Design agent state management and session persistence using PostgreSQL / Redis
- Implement task queuing, scheduling, and async execution for long-running agent workflows
- Build and register custom agent tools for file processing, web search, SQL querying, SFTP operations, and third-party API calls
- Implement guardrails and output validators to ensure agent responses meet business and compliance requirements
- Develop comprehensive error handling, retry strategies, and graceful degradation patterns for agent failures
- Instrument agents with end-to-end tracing (LangSmith, Arize, custom logging) across reasoning steps and tool calls
- Build evaluation pipelines to measure agent accuracy, latency, tool-use correctness, and goal completion rates
Mandatory skill sets
- Python (advanced) - async programming, OOP, design patterns
- LangChain, LangGraph, AutoGen, CrewAI, or equivalent
- OpenAI API, Anthropic Claude, HuggingFace Transformers
- FastAPI, REST, Streaming APIs (SSE / WebSockets)
- CoT, ReAct, structured outputs, function calling
- Pandas, structured/unstructured data parsing
- Redis, Kafka, or RabbitMQ for event-driven agent triggers
- PostgreSQL for state/session management
Preferred skill sets
- Experience with fine-tuning or RLHF pipelines for domain-specific LLMs
- Familiarity with Model Context Protocol (MCP) for standardized tool integration
- Knowledge of open-source LLM deployment (Ollama, vLLM, LiteLLM)
- Understanding of AI safety principles, responsible AI, and model risk management
- Experience with browser-use or computer-use agents for UI automation tasks
Experience
- 3+ years of overall software/data/AI engineering experience
- 1-2 years of hands-on experience building LLM-based applications or AI agent systems
- Demonstrated experience shipping production-grade agentic workflows
- Strong foundation in backend system design with event-driven and microservices architecture
Education qualification
- Bachelor's degree in Computer Science, Information Technology, or a related field.
- Proven experience of 3+ YEARS with Automation Anywhere and other RPA tools.
- Strong analytical and problem-solving skills.
- Effective communication skills to work with various stakeholders.
- Ability to work independently as well as in a team environment.
- Detail-oriented with a focus on delivering high-quality work.
Salary
- Not specified
Travel Requirements
- Not Specified
Job details
- Published
- September 1, 2026
- Job source
- myworkdayjobs
- Workplace
- On-site · Bengaluru, IN
- First seen
- September 1, 2026
See how well you match this job
Log in or sign up and Eva will compare your profile with this role, explain your strengths and show what to improve.
Sign up to see your matchAlready have an account? Log inMore at PricewaterhouseCoopers Services LLP
Similar jobs from this company
None listed.
Across the market
Similar jobs from other companies
- Agentic AI DeveloperPricewaterhouseCoopers Services LLPBengaluru, INOn-site
- Agentic AI DeveloperPrometteur Solutions Pvt. Ltd.Pune, INOn-site
- Agentic AI DeveloperJPI Employment Services, LLCDallas OfficeOn-site
- Agentic AI DeveloperBooz Allen Hamilton_United StatesArlington, VAOn-site
- Agentic AI DeveloperASI GovernmentWashington, USOn-site
- Agentic AI DeveloperOSEDEAMontreal, CAHybrid
Third-party content disclaimer
Full job descriptions are sourced directly from third-party applicant tracking systems (ATS), job boards, recruitment platforms, and employer career pages.
LiftmyCV does not claim ownership of this content or guarantee its accuracy or current availability. All original content is the intellectual property of the respective employers or other rights holders.
LiftmyCV hiring intelligence, availability checks, and related-job recommendations are generated from LiftmyCV data and public sources.
If you prefer, you may apply directly via the original listing for transparency.