2 days ago
Bengaluru, IndiaMid Level / Senior
Responsibilities
- Design and develop autonomous and semi-autonomous multi-agent systems with planning, reasoning, memory, inter-agent communication, and tool use.
- Implement agent orchestration with LangGraph, AutoGen, CrewAI, LangChain, or custom frameworks.
- Integrate LLM providers, prompt templates, structured outputs, function calling, RAG pipelines, validation, retries, and fallback logic.
- Build FastAPI-based agent services, event-driven triggers, asynchronous task execution, state management, and session persistence.
- Create tools for file processing, web search, SQL querying, SFTP, and third-party API integration across structured and unstructured data sources.
- Connect agents to vector databases and external systems through MCP or custom tool registries.
- Implement guardrails, output validation, human-in-the-loop checkpoints, sandboxing, error handling, and graceful degradation.
- Instrument and evaluate agents using tracing, metrics, audit logs, and KPIs such as task success, hallucination, and escalation rates.
Requirements
- Advanced Python programming skills, including asynchronous programming, object-oriented programming, and design patterns.
- Four to seven years of experience in relevant development work.
- Experience with agent frameworks such as LangChain, LangGraph, AutoGen, or CrewAI and LLM APIs including OpenAI API, Anthropic Claude, or HuggingFace Transformers API.
- Experience developing FastAPI services and streaming APIs using SSE or WebSockets.
- Knowledge of prompt engineering, chain-of-thought, ReAct, structured outputs, and function calling.
- Experience with Pandas, structured and unstructured data parsing, Redis, Kafka, RabbitMQ, and PostgreSQL.
- Experience with logging, tracing using LangSmith or OpenTelemetry, and metrics.
- Bachelor of Technology or equivalent listed qualifications including BE, BTech, MCA, MTech, or MBA.
- Preferred: fine-tuning or RLHF pipelines, MCP, Ollama, vLLM, LiteLLM, Kubernetes, data engineering or ingestion platforms, AI safety, responsible AI, model risk management, and browser-use or computer-use agents.
Benefits
- Inclusive work environment with equal employment opportunities and zero tolerance for discrimination and harassment.
- Flexible programs, wellbeing support, mentorship, learning opportunities, and opportunities to contribute to client and community outcomes.
- Work location listed as Bangalore; the posting does not specify a remote or hybrid arrangement.
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.