2 days ago
Responsibilities
- Design and develop autonomous and semi-autonomous agents capable of multi-step reasoning, planning, and decision-making.
- Build multi-agent systems with defined roles, inter-agent communication, memory layers, orchestration, tool use, and function calling.
- Integrate LLM providers and implement prompt templates, structured outputs, RAG, validation, fallback, and retry logic.
- Build FastAPI-based services and REST or streaming APIs for agent capabilities.
- Develop event-driven triggers, task queuing, scheduling, asynchronous execution, state management, and session persistence.
- Create tools for file processing, web search, SQL querying, SFTP operations, and third-party API integration.
- Connect agents to structured and unstructured data sources and vector databases.
- Implement guardrails, human-in-the-loop checkpoints, sandboxing, execution boundaries, error handling, and graceful degradation.
- Instrument and evaluate agents using tracing, logging, metrics, KPIs, and audit logs.
- Apply agentic AI and RPA solutions to enterprise use cases such as document processing, workflow automation, data enrichment, and conversational AI.
Requirements
- At least 3 years of overall software, data, or 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 rather than only prototypes.
- Strong backend system design experience with event-driven and microservices architecture.
- Advanced Python skills, including asynchronous programming, object-oriented programming, and design patterns.
- Experience with LangChain, LangGraph, AutoGen, CrewAI, or equivalent agent frameworks.
- Experience with OpenAI API, Anthropic Claude, or HuggingFace Transformers API.
- Experience with FastAPI, REST, streaming APIs, prompt engineering, structured outputs, and function calling.
- Experience with Pandas, structured and unstructured data parsing, Redis, Kafka or RabbitMQ, PostgreSQL, and observability tooling.
- At least 3 years of experience with Automation Anywhere and other RPA tools.
- Bachelor's degree in Computer Science, Information Technology, engineering, or a related field.
- Strong analytical, problem-solving, communication, independent-working, teamwork, and detail-oriented skills.
- Preferred qualifications include LLM fine-tuning or RLHF, MCP, Ollama, vLLM, LiteLLM, Kubernetes, data engineering, AI safety, responsible AI, model risk management, and browser-use or computer-use agents.
Benefits
- PwC offers inclusive benefits, flexibility programs, wellbeing support, mentorship, and opportunities for learning and career growth.
- The role is based in Bangalore, India; travel requirements are not specified.
- Visa sponsorship is not available.
Tech Stack
Categories
About PwC
At PwC, we help clients drive their companies to the leading edge. We’re a tech-forward, people-empowered network with more than 370,000 people in 149 countries. Across audit and assurance, tax and legal, deals and consulting we help build, accelerate and sustain momentum. Find out more at www.pwc.com. PwC: Audit and assurance, consulting and tax services PwC refers to the PwC network and/or one or more of its member firms, each of which is a separate legal entity. Content on this page has been prepared for general information only and is not intended to be relied upon as accounting, tax or professional advice. Please reach out to your advisors for specific advice.