Senior AI Full Stack Developer (Python & React)

About us

Accenture Industry X, part of Accenture, helps organizations thrive in the digital era by combining deep industry expertise with data, AI, cloud, and digital engineering capabilities.

We partner with leading organizations across industries to design and deliver intelligent, scalable solutions that create measurable business value and transform the way companies operate.

About the team

At Accenture, we are at the forefront of the AI evolution, working with global clients to transform their businesses into AI-enabled enterprises.

Our teams design and build next-generation Generative AI and Agentic AI solutions , ranging from intelligent applications and AI agents to enterprise-grade AI platforms, RAG architectures, and observability capabilities.

We work in fast-moving, cross-functional teams where software engineering, AI, cloud, architecture, design, and business strategy come together.

We are looking for an experienced Senior AI Full Stack Developer  with strong expertise in Python and React/TypeScript  who can design, build, and deploy production-grade AI applications from end to end.

Your Role

As a Senior AI Full Stack Developer, you will be responsible for developing modern AI-powered applications across the complete technology stack — from Python backend services and AI orchestration layers to responsive React-based user experiences.

You will work hands-on with Large Language Models (LLMs), Generative AI, Agentic AI, Retrieval-Augmented Generation (RAG), APIs, cloud platforms, and modern DevOps practices , turning AI concepts and prototypes into secure, scalable, observable, production-ready solutions.

Key Responsibilities

• Design, develop, and maintain end-to-end AI-powered applications  using Python and React/TypeScript.

• Build scalable backend services and REST APIs  using Python frameworks such as FastAPI, Flask, or Django .

• Develop modern, responsive, and reusable front-end applications using React, TypeScript, Next.js, HTML, and CSS .

• Integrate front-end applications with backend services, AI services, enterprise APIs, and data platforms.

• Design and implement Generative AI and Agentic AI applications  powered by Large Language Models.

• Build AI workflows and agent-based systems using frameworks such as LangChain, LangGraph, LlamaIndex, Haystack , or similar technologies.

• Design and implement Retrieval-Augmented Generation (RAG)  pipelines, including document ingestion, chunking, embedding generation, retrieval, reranking, and response generation.

• Integrate vector databases and search technologies such as Pinecone, Weaviate, FAISS, Milvus, Azure AI Search, Elasticsearch , or equivalent solutions.

• Integrate commercial and open-source LLMs through platforms and APIs such as Azure OpenAI, OpenAI, AWS Bedrock, Google Vertex AI, Hugging Face , or similar services.

• Apply prompt engineering, structured outputs, tool/function calling, context management, and model evaluation  techniques to improve AI application quality and reliability.

• Implement AI agent capabilities including tool usage, workflow orchestration, memory/state management, multi-agent patterns, and human-in-the-loop workflows  where appropriate.

• Implement appropriate LLM evaluation, tracing, monitoring, guardrails, and observability  mechanisms for production AI systems.

• Optimize AI applications for accuracy, latency, scalability, reliability, and cost .

• Design secure application architectures covering authentication, authorization, API security, secrets management, and secure handling of enterprise data.

• Deploy and operate applications in AWS, Microsoft Azure, or Google Cloud Platform (GCP) .

• Containerize applications using Docker  and work with orchestration platforms such as Kubernetes .

• Implement infrastructure and deployment automation using Infrastructure as Code (IaC)  technologies such as Terraform.

• Build and maintain CI/CD pipelines  and apply DevOps, MLOps, LLMOps, and AIOps practices.

• Implement application and AI observability through logging, metrics, tracing, monitoring, and alerting.

• Write clean, maintainable, reusable, well-documented, and testable code across the full technology stack.

• Implement unit, integration, API, and end-to-end testing to ensure application quality.

• Participate in architecture and technical design discussions and contribute to technology and engineering decisions.

• Perform code reviews, establish engineering best practices, and support other developers through technical guidance and knowledge sharing.

• Collaborate closely with AI engineers, software engineers, architects, data engineers, DevOps engineers, designers, product owners, and client stakeholders.

• Evaluate emerging AI technologies and determine how they can be applied effectively in enterprise environments.

• Take ownership of solutions from concept and prototyping through production deployment, monitoring, and continuous improvement .

What you need to succeed

We are looking for an experienced software engineer who combines strong full-stack engineering fundamentals  with hands-on experience building modern AI applications.

Core Technical Skills

• Strong professional experience with Python  and modern Python software development.

• Strong professional experience with React and TypeScript .

• Experience developing production-grade backend services using FastAPI, Flask, Django , or similar frameworks.

• Strong understanding of REST APIs, asynchronous programming, microservices, distributed systems, and API integration .

• Experience building modern front-end architectures, reusable components, state management, API integration, and responsive user interfaces.

• Strong understanding of software engineering principles, including clean code, design patterns, testing, version control, and code review practices .

• Experience working with relational and/or NoSQL databases such as PostgreSQL, MySQL, MongoDB, Redis , or equivalent technologies.

Generative AI & Agentic AI

• Hands-on experience developing applications powered by Large Language Models (LLMs) .

• Experience with Generative AI, Agentic AI, prompt engineering, tool/function calling, and structured LLM outputs .

• Experience with AI orchestration frameworks such as LangChain, LangGraph, LlamaIndex, Haystack , or similar technologies.

• Practical experience designing and implementing RAG architectures .

• Experience with embeddings, semantic/vector search, retrieval strategies, reranking, and vector databases .

• Understanding of common LLM challenges including hallucinations, context limitations, prompt injection, latency, cost, security, and evaluation .

• Experience implementing LLM observability, evaluation, tracing, and guardrails .

• Knowledge of fine-tuning approaches such as LoRA and PEFT  is an advantage.

Cloud & DevOps

• Hands-on experience with at least one major cloud platform: Microsoft Azure, AWS, or GCP .

• Experience with Docker  and containerized application development.

• Experience with Kubernetes  or equivalent container orchestration technologies.

• Experience implementing CI/CD pipelines .

• Familiarity with Infrastructure as Code , preferably Terraform.

• Understanding of DevOps, MLOps, LLMOps, AIOps, monitoring, logging, and distributed tracing .

• Experience designing scalable, resilient, secure, and observable production systems.

Nice to Have

• Experience designing multi-agent or complex agentic workflows .

• Experience with event-driven architectures and messaging technologies such as Kafka or RabbitMQ.

• Experience with streaming AI responses and technologies such as WebSockets or Server-Sent Events.

• Experience with enterprise authentication and authorization standards such as OAuth 2.0, OpenID Connect, and JWT .

• Experience with AI observability and evaluation platforms.

• Experience working with enterprise search, knowledge management, or document-