AI Engineer GenAI & Multi-Agent Systems

AI Engineer – GenAI & Multi-Agent Systems

About Mu Sigma

Mu Sigma Business Solutions Pvt. Ltd Big Data tops many a list of business priorities, thanks to its growing volume, velocity, and variety. However, it is not data, but change that is the cause of anxiety to organization, bringing with it greater complexity and more data. The challenge here is that analytical thinking isn't keeping pace with the rate of change in business. This is where we come in – we address the gaps. Mu Sigma is the world's largest pure play Decision Sciences and analytics firm. We help over 140 Fortune 500 clients across more than 10 industry verticals, to institutionalize data-driven decision making in a cost-effective and scalable manner. We provide our clients with a holistic ecosystem of proprietary technology platforms, processes and people. Our unique approach to problem solving using cross-industry expertise corroborates our sustainable engagement model with our clients still further, making us one of the most preferred analytics and Decision Sciences partners. With over 3500 Decision Sciences professionals, we pride ourselves in being a category and career defining company. As we continue to scale, we are also looking at hiring the right talent across various levels in our organization.

Role Overview

We are looking for a highly skilled AI Engineer specializing in Generative AI and Multi-Agent Systems to design and deploy intelligent, autonomous solutions. This role focuses on building LLM-powered, agent-driven architectures that can reason, collaborate, and execute complex workflows across enterprise systems.

You will work on cutting-edge Agentic AI frameworks, enabling systems that go beyond prediction to decision-making, orchestration, and autonomous execution.

Key Responsibilities

• Design and build multi-agent AI systems capable of planning, reasoning, and task execution
• Develop applications using LLMs (GPT, Claude, Llama, etc.) with advanced prompt engineering and orchestration
• Implement Agentic workflows (planner → executor → critic → memory loops)
• Build RAG (Retrieval-Augmented Generation) pipelines with vector databases for enterprise knowledge grounding
• Develop tool-using agents that integrate with APIs, databases, and enterprise systems
• Architect and deploy AI copilots and autonomous assistants for business workflows
• Optimize LLM performance using fine-tuning, prompt chaining, and caching strategies
• Implement short-term and long-term memory mechanisms (vector stores, knowledge graphs)
• Design multi-agent collaboration protocols (hierarchical, swarm, role-based agents)
• Deploy scalable solutions using MLOps + LLMOps practices (monitoring, evaluation, guardrails)
• Ensure AI safety, governance, and responsible AI practices

Required Skills & Qualifications

• Bachelor's/Master's in Computer Science, AI, or related field
• 3–8 years experience in AI/ML with strong focus on Generative AI
• Strong Python development skills
• Hands-on experience with:
• LLMs & GenAI frameworks: OpenAI, Hugging Face Transformers
• Agent frameworks: LangChain, AutoGen, CrewAI, Semantic Kernel
• RAG pipelines & vector DBs: FAISS, Pinecone, Weaviate
• Experience building API-driven, tool-integrated AI agents
• Strong understanding of:
• Prompt engineering & prompt optimization
• Chain-of-thought reasoning and tool augmentation
• Context management and token optimization
• Experience with cloud platforms (Azure OpenAI preferred, AWS/GCP acceptable)
• Knowledge of Docker, Kubernetes, CI/CD pipelines

Preferred Qualifications

• Experience building multi-agent orchestration systems with role-based coordination
• Exposure to agent planning algorithms (ReAct, Plan-and-Execute, Tree-of-Thought)
• Experience with LLM evaluation frameworks (RAGAS, TruLens, Promptfoo)
• Knowledge of graph-based reasoning / knowledge graphs
• Building autonomous systems or copilots in enterprise environments
• Domain experience in industrial, energy, or IoT environments

Key Competencies

• Systems thinking for designing autonomous AI architectures
• Strong problem decomposition for agent task design
• Ability to balance latency, cost, and accuracy in LLM systems
• Communication with business stakeholders to translate workflows into agent pipelines
• Innovation mindset with focus on applying agentic AI in production

Tech Stack (Modern GenAI Stack)

• Languages: Python
• Frameworks: LangChain, CrewAI, AutoGen, Semantic Kernel
• LLMs: OpenAI GPT, Azure OpenAI, Claude, Llama
• Vector DB: Pinecone, Weaviate, FAISS
• Orchestration: Airflow, Prefect
• Deployment: Docker, Kubernetes
• Cloud: Azure AI Studio / Azure ML (preferred)

KPIs / Success Metrics

• Autonomous task completion rate of agents
• Reduction in manual workflows via AI automation
• Latency and cost optimization of LLM pipelines
• Accuracy and reliability of agent outputs
• Adoption rate of AI copilots across teams