AI Engineer – GenAI & Agentic AI

Kitron; Chennai District; On-site; INR 1,200,000 - 2,000,000; Full time

Benefits offered by this job

Global projects

Training and development courses

Job summary

Kitron is seeking an AI Engineer to develop and deploy AI applications, including generative AI, RAG, and agentic workflows, across business and manufacturing use cases. You will integrate AI with REST APIs, databases, and enterprise tools, while evaluating models for performance, reliability, and security.

ideal candidates have hands-on Python, experience with LLMs and embeddings, and a background in cloud/on-prem deployment using Docker.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, Electronics, IT, or a related field.

Responsibilities

• Develop AI applications and POCs for business, operations, engineering, and manufacturing use cases.

Skills

Python

LLMs

RAG

REST APIs

Docker

Linux

CI/CD

Cloud deployment

Azure OpenAI

Embeddings

Vector DBs

Semantic search

Agentic AI

Knowledge retrieval

Git

Communication

Education

Bachelor’s or Master’s degree in CS/AI/DS

Tools

LangGraph

Semantic Kernel

Microsoft Agent Framework

Microsoft Foundry

Azure OpenAI

Job description

About Kitron

Kitron is a leading Scandinavian Electronics Manufacturing Services (EMS) company, delivering improved flexibility, cost efficiency, and innovation power through the value chain. The company has operations in Norway, Sweden, Denmark, Lithuania, Germany, Poland, the Czech Republic, India, China,Malaysia, and the United States. With 2500 highly skilled employees, Kitron manufactures and delivers anything from fully assembled electronic circuit boards to complete end - products for customers globally. Related technical services like prototyping, industrialisation, material analysing and test development are also key competencies offered by Kitron.

Our values

Location: Chennai
Deadline: 2026.10.28

Job Description:

• Develop AI applications and POCs for business, operations, engineering, and manufacturing use cases.
• Build Generative AI solutions using LLMs such as GPT, Claude, Gemini, Llama, Phi, or similar models.
• Develop RAG solutions using company documents, databases, and enterprise knowledge.
• Design and develop AI agents and agentic workflows for multi-step business tasks, decision-making, and tool/API usage.
• Integrate AI solutions with REST APIs, databases, enterprise applications, and approved tools.
• Develop human-in-the-loop workflows for validation, approval, and exception handling.
• Build backend services, data-processing workflows, and supporting APIs for AI applications.
• Evaluate AI models and solutions based on accuracy, reliability, performance, cost, and security.
• Use Microsoft Azure AI, Microsoft Foundry, Azure OpenAI, or other suitable AI platforms.
• Develop and deploy AI applications using Docker in cloud or on-premise environments.
• Conduct technical feasibility studies, rapid prototyping, POCs, testing, and deployment.
• Collaborate with business, IT, software, engineering, and other technical teams to deliver practical AI solutions.
• Prepare solution architecture, technical documentation, and POC/evaluation reports.
• Continuously explore emerging Generative AI, Agentic AI, models, and frameworks.

Requirements:

• Bachelor’s or Master’s degree in Computer Science, AI, Data Science, Electronics, IT, or a related field.
• 2–5 years of experience in AI engineering, software engineering, Generative AI, or related application development.
• Strong hands-on experience in Python and software development.
• Practical experience with LLMs, RAG, embeddings, vector databases, semantic search, and knowledge retrieval.
• Experience developing AI agents, agentic workflows, tool/function calling, or multi-step AI applications.
• Experience with frameworks such as Microsoft Agent Framework, Semantic Kernel, LangGraph, or equivalent.
• Strong experience with REST APIs, SQL databases, and system integration.
• Experience with Git, Docker, Linux, CI/CD, and cloud or on-premise deployment.
• Familiarity with Microsoft Azure, Microsoft Foundry, or Azure OpenAI is preferred.
• Understanding of AI evaluation, structured outputs, prompt engineering, hallucination mitigation, and responsible AI.
• Strong problem-solving skills with the ability to convert business requirements into practical AI solutions.
• Good communication skills and ability to work with technical and non-technical stakeholders.
• Ability to independently take an AI use case from assessment and architecture through POC, evaluation, and deployment.
• Exposure to computer vision, manufacturing, engineering, automation, or robotics is an added advantage.
• Willingness to continuously learn and experiment with emerging AI technologies.

We offer:

• Global team and projects
• Opportunities for personal and professional development
• Training and competence development courses.