Artificial Intelligence Engineer

Location - Gurugram / Bangalore

As a partner to businesses and governments, Crane Authentication offers expertise and cutting-edge innovations that protect and enhance products, secure identities, safeguard revenues and enforce compliance. Customers from different business sectors and levels of government trust our team of 1,250 people for their expertise in R&D, security design, engineering and data-driven insights. We are an integral part of Crane NXT , a c$2 billion dollar business with over 5,000 associates

Summary :

Crane Authentication provides a range of software platforms with sophisticated anti-counterfeit, anti-piracy, anti-fraud capabilities and track and trace solutions capable of handling billions of transactions per day. Our customers are global brands and Governments.

We are seeking a highly skilled and forward-thinking AI Engineer experienced in designing, deploying, and operationalizing modern AI solutions using Generative AI , Agentic AI frameworks , Retrieval-Augmented Generation (RAG) , and Model Context Protocol (MCP) for intelligent multi-agent orchestration.

In this role, you’ll build context-aware AI agents capable of dynamic memory management, tool-based reasoning, multi-modal interaction, and consistent state maintenance across distributed AI ecosystems. You’ll work at the forefront of autonomous AI system design integrating multi-model workflows, RAG pipelines, tool-augmented agents, and persistent context protocols.

Key Accountability :

Design, develop, and deploy advanced AI systems leveraging LLMs , multi-modal models , and autonomous agent frameworks .

Architect and implement Retrieval-Augmented Generation (RAG) pipelines integrated with vector databases for dynamic, enterprise-safe context retrieval.

Develop and manage context-aware AI agents leveraging Model Context Protocol (MCP) or equivalent structured context management mechanisms for persistent memory, multi-agent collaboration, and session continuity.

Implement context propagation, state serialization, and contextual handoff mechanisms across distributed agents, tools, and reasoning chains.

Integrate AI systems with cloud APIs, vector databases, plugin architectures, and orchestration frameworks for multi-step task execution.

Optimize memory management, prompt engineering, and dynamic context windows for complex, long-running AI workflows.

Lead AI agent orchestration initiatives using frameworks like LangChain , Semantic Kernel , CrewAI , or AutoGen , with MCP integration for context tracing and governance.

Stay ahead of emerging trends in multi-agent LLM ecosystems , autonomous reasoning frameworks , and context-aware AI protocol standards like MCP.

Required Experience :

3+ years of AI engineering experience, with direct expertise in :

Generative AI (GenAI) frameworks (OpenAI, Hugging Face, Anthropic, Mistral)

Agentic AI orchestration frameworks (LangChain, Semantic Kernel, AutoGen, CrewAI)

Retrieval-Augmented Generation (RAG) system design and deployment

Model Context Protocol (MCP) or structured context management solutions in multi-agent, multi-tool AI workflows

Strong software engineering skills in Python , including AI / ML libraries like PyTorch , TensorFlow , Transformers , and RAG toolkits.

Hands-on experience working with vector databases (Pinecone, FAISS, Weaviate, Chroma) and plugin-based AI architectures .

Strong understanding of AI memory management, session context propagation, and multi-agent communication protocols.

Programming framework / language : Python, JS or Java.

Vector databases (Pinecone, FAISS, Weaviate, Chroma) and plugin-based AI architectures .

Experience with ML frameworks like TensorFlow, PyTorch, or Scikit-learn.

Solid understanding of statistics, data structures, and algorithms.

Preferred Skills :

Experience integrating multi-modal models (text, image, audio, video) into agentic workflows.

Familiarity with AI safety, observability, and context integrity management in distributed AI systems.

Exposure to LLMOps pipelines , prompt optimization techniques, and AI agent performance tuning.

Experience contributing to open-source AI orchestration frameworks or context management libraries.

Understanding of AI alignment, ethical AI principles, and responsible AI design.

Experience with Deep learning in NLP, computer vision, or reinforcement learning.

Education Qualification :

Bachelor’s or Master’s degree in Computer Science, Machine Learning, or a related field.

4+ years of experience working as a software engineer developing commercial software.

Experience using collaborative tools such as : Slack, Microsoft Teams, and Jira.

Common to all roles

To ensure full participation in the performance development review (PDR) process and maintain an up-to-date record of all training and development activities / programs.

To always act and behave in a way compliant with all Crane Authentication’s company guidelines and policies, especially those relating to values and behaviours, environmental health and safety, ethics and codes of conduct, as it is through living our values that we strengthen the culture of our business and demonstrate our understanding of our Code of Business Principles. Further information on our company values can be found in our “Living the Values” guidelines.

Crane Authentication is part of Crane NXT

Crane NXT is a premier industrial technology company that provides proprietary and trusted technology solutions to secure, detect, and authenticate what matters most to its customers. Crane NXT has approximately 5,000 employees with global operations and manufacturing facilities in the United States, the United Kingdom, Mexico, Japan, Switzerland, Germany, Sweden, and Malta. For more information, visit www.cranenxt.com.

We value diversity at our company. Everyone who applies with the qualifications will receive consideration for employment without regard to : age, colour, national origin, citizenship status, physical or mental disability, race, religion, creed, gender, sex, sexual orientation, gender identity and / or expression, genetic information, marital status, status with regard to public assistance, veteran status, or any other characteristic protected by law.

We receive a high number of applications, so apologies if we are unable to provide specific feedback. If we feel you are a fit for the role, we’ll be in contact.