- Experience
- Any
- Salary
- —
- Openings
- 1
- Posted
- 10 jam yang lalu
- Work mode
- In office
- Resume
- Required to apply
Where you'll work
Job description
About the Position
Join Accenture to be part of a transformative journey that impacts top global organizations and communities. Leverage your skills in a dynamic environment focused on innovation, collaboration, and value delivery, fostering significant career growth.
Role Overview
As a Full Stack Large Language Model (LLM) Developer, you will engineer complete applications powered by advanced LLM technology to address intricate business challenges. Your contributions will span front-end user experiences, back-end service implementations, and orchestration of LLM workflows, ensuring secure, scalable, and enterprise-ready AI solutions.
Core Responsibilities
- Develop comprehensive full stack applications integrating LLMs within user workflows and organizational processes.
- Construct backend APIs for prompt orchestration, support retrieval-augmented generation (RAG), and enable API/tool interactions.
- Create responsive and user-friendly frontend interfaces allowing effective engagement with LLM features.
- Connect applications to enterprise data repositories, vector databases, and apply authentication and authorization protocols.
- Collaborate with architects, data engineers, and product owners to transform business needs into robust technical solutions.
- Implement monitoring, logging, and performance tracking for LLM interactions and overall application health.
- Adopt secure coding methodologies and assist in establishing ethical AI usage guardrails.
- Engage in code reviews, technical design discussions, and contribute to ongoing engineering practice enhancements.
Mandatory Qualifications
- Proven experience in full stack software application development.
- Expertise in at least one backend programming language/framework such as Node.js, Python, Java, or .NET.
- Familiarity with modern frontend frameworks including React, Angular, or Vue.
- Practical experience integrating with Large Language Models, including platforms like Azure OpenAI or OpenAI.
- Comprehensive understanding of RESTful APIs, microservices architecture, and serverless or event-driven systems.
- Experience with relational and/or NoSQL databases and foundational knowledge of vector database technologies.
- Exposure to cloud computing platforms such as Azure, AWS, or GCP along with CI/CD pipelines.
- Strong analytical and problem-solving skills within agile and cross-disciplinary teams.
Desirable Qualifications
- Hands-on experience designing retrieval-augmented generation (RAG) pipelines or chat/workflow applications powered by LLMs.
- Understanding of LLMOps, including prompt management, version control, evaluation, and safety mechanisms.
- Knowledge of enterprise authentication and authorization frameworks like OAuth2 and OpenID Connect.
- Experience operating within regulated sectors such as banking, finance, or compliance.
- Familiarity with containerization and orchestration technologies, including Docker and Kubernetes.
Team and Company Culture
You will be a part of Accenture’s AI and Intelligent Platforms division, collaborating closely with architects, data engineers, and domain specialists to craft cutting-edge, production-ready AI solutions. The team prioritizes measurable business impact and nurtures a spirit of experimentation, continual learning, and teamwork.
Accenture is committed to equal opportunity employment, welcoming applications from individuals regardless of race, religion, ethnicity, disability, age, citizenship, marital or civil status, sexual orientation, or gender identity, in line with applicable laws.