Large Language Model (LLM) Architect
Client: Accenture
Location: Bengaluru
Experience: 3+ Years
Job Type: Full-time
Education: Bachelor's Degree (15 years of full-time education)
About the Role
We are looking for a Large Language Model (LLM) Architect to design and build enterprise-scale AI systems powered by Large Language Models and multi-agent architectures. You will be responsible for architecting scalable AI solutions, evaluating LLM frameworks, implementing Retrieval-Augmented Generation (RAG), and enabling intelligent agent orchestration for complex business use cases.
This role is ideal for professionals with hands-on experience in Generative AI, LLM orchestration, AI agents, and enterprise AI architecture.
Key Responsibilities
- Design end-to-end enterprise AI architectures leveraging Large Language Models (LLMs).
- Architect intelligent multi-agent systems and agent orchestration workflows.
- Evaluate and implement LLM frameworks, models, APIs, and orchestration platforms.
- Design Retrieval-Augmented Generation (RAG) solutions using hybrid search and enterprise knowledge bases.
- Build scalable AI solutions with function calling, Model Context Protocol (MCP), API integrations, and Agent-to-Agent (A2A) communication.
- Implement plan-and-execute strategies for autonomous AI workflows.
- Design secure, scalable, and cost-efficient AI systems with optimized token usage and context-window management.
- Develop AI safety strategies, including prompt protection, threat modeling, and responsible AI practices.
- Collaborate with cross-functional engineering teams to deliver enterprise-ready AI solutions.
- Lead technical assessments, proof-of-concepts (POCs), and production deployments.
Required Skills
- Hands-on experience with Large Language Models (LLMs).
- Strong understanding of RAG (Retrieval-Augmented Generation) and hybrid search architectures.
- Experience with LLM orchestration frameworks such as:
- LangGraph
- CrewAI
- AutoGen
- Vertex AI
- AI Refinery
- Experience building AI agents, multi-agent systems, and agent orchestration.
- Strong knowledge of:
- Function Calling
- API Integration
- MCP (Model Context Protocol)
- Agent-to-Agent (A2A) Communication
- Experience with enterprise AI architecture and cloud-native environments.
- Understanding of AI security, prompt protection, and GenAI threat modeling.
- Strong system design and architecture skills.
Preferred Skills
- Experience with cloud platforms such as AWS, Azure, or Google Cloud.
- Knowledge of API Gateway design and performance optimization.
- Experience with token optimization and context-window management.
- Familiarity with enterprise integration patterns and scalable AI deployments.
Eligibility Criteria
- Minimum 3 years of experience in Large Language Models (LLMs).
- Strong experience in enterprise AI architecture and GenAI solutions.
- Bachelor's degree or equivalent with 15 years of full-time education.
- Willingness to work from Bengaluru.
Pay: ₹1,200,000.00 - ₹17,999,518.00 per year
Application Question(s):
- How many years of hands-on experience do you have working with Large Language Models (LLMs)?
- Which LLMs have you worked with?
- Which LLM orchestration frameworks have you worked with?
- This role is for Accenture. Have you applied to or interviewed with Accenture in the last six months? If yes, please share the role and interview/application date.
- Are you open to working from Bengaluru?
- CTC
- ECTC
- Notice Period
Work Location: In person
