Platform Engineer II at HCLTech in Bengaluru, Karnataka, IN

Job Summary

As an Agentic AI Engineer II, you will work as a hands-on developer in the Cloud Native COE, building GenAI and agentic AI components under the guidance of senior architects and technical leads. You will write, test and maintain code for LLM-based agents, tool integrations and RAG pipelines, turn architect-defined designs into working proofs of concept and solution accelerators, and help bring them to production-ready quality.

This role suits engineers with 2–3 years of hands-on coding experience in Python and/or Java who want to deepen their skills in GenAI, agentic AI and cloud-native engineering by learning on the job.

Key Responsibilities

• Develop, test and debug agentic AI and GenAI components, such as LLM agents, tool/function calling and RAG pipelines, based on designs provided by architects
• Design and optimize prompts for different LLMs, and evaluate model outputs to improve accuracy and reliability
• Integrate LLM APIs (e.g., OpenAI, Azure OpenAI, AWS Bedrock) and vector databases with enterprise data sources
• Build and maintain POCs, demos and reusable code components for customer use cases, including legacy modernization use cases
• Implement guardrails, logging and monitoring for AI services as directed by the technical lead
• Deploy and run services on cloud platforms (AWS, Azure or Google Cloud) using the team’s CI/CD pipelines and DevOps tools
• Prepare technical documentation, code walkthroughs and demo notes for architects and delivery teams
• Take part in code reviews, sprint ceremonies and internal knowledge-sharing sessions

Skill Requirements

• Programming & frameworks: Hands-on Python and/or Java; working experience with TensorFlow or PyTorch
• GenAI: Proficiency in GenAI frameworks and libraries such as OpenAI; prompt engineering – designing and optimizing prompts for various AI models to achieve the desired outputs and improve model performance

AI/ML: Proficiency in core ML concepts and algorithms; knowledge of deep learning techniques and neural networks; understanding of NLP techniques and tools, including tokenization, embeddings,

• transformers and language models; knowledge of vector databases and LLMs, and of integrating applications with them
• Cloud computing: Experience working with cloud services on AWS, Azure or Google Cloud
• DevOps: Knowledge of DevOps practices and tools (e.g., Git, CI/CD pipelines, Docker)
• Communication: Strong communication and articulation skills
• Problem solving: Ability to identify issues and come up with effective solutions
• Learnability & adaptability: Enthusiasm to learn new technologies; a quick learner who can learn on the job

Good to Have:

• Exposure to agentic AI frameworks such as LangChain, LangGraph, CrewAI or MCP
• Experience building REST APIs (e.g., FastAPI, Flask or Spring Boot)
• Working knowledge of SQL and NoSQL databases

Other Requirements

Team & Client Interaction:

• Support architects in customer workshops, demos and POC presentations by preparing and running technical demos
• Explain your work clearly to team members and, when required, to client technical teams
• Work closely with architects, senior engineers, and data and platform teams to deliver assigned tasks on time and to agreed quality standards

Learning & Growth:

• Stay current with new GenAI, agentic AI and cloud-native tools and frameworks, and share what you learn with the team
• Pick up new technologies quickly and apply them on the job

Experience:

• 2–3 years of hands-on coding experience in Python and/or Java
• Working experience with ML/DL frameworks such as TensorFlow or PyTorch
• Hands-on experience using GenAI frameworks and libraries such as OpenAI, and in designing and optimizing prompts for LLMs
• Experience working with cloud services on AWS, Azure or Google Cloud

Education:

• Bachelor’s or master’s degree in Engineering, Computer Science, or a related field
• GenAI or cloud certifications (AWS, Azure, GCP) are an advantage but not mandatory