Generative AI Platform Engineering

Ciklum; Chennai District, Pune District; On-site; INR 900,000 - 1,500,000; Full time

Job summary

Ciklum is seeking a Senior GenAI Platform Engineer in Chennai to design, develop, and deploy enterprise-grade GenAI platform solutions. You will build scalable LLM, RAG, and Agentic AI applications and develop secure APIs and microservices for AI workloads.

The role emphasizes automated CI/CD/DevSecOps, cross-functional collaboration, and optimizing platform performance for scalability and reliability in cloud-native environments.

Qualifications

• Strong Python expertise.
• Experience with Generative AI, LLMs, and Prompt Engineering.
• Hands-on experience with RAG and Agentic AI.
• Knowledge of Model Context Protocol (MCP).
• Strong Data Engineering fundamentals and data pipeline development.
• Experience with Kubernetes, Docker, and Containerized Applications.
• Cloud experience with AWS, Azure, or GCP.
• CI/CD, DevSecOps, Infrastructure as Code, and automation.
• Experience with Kafka/Event Streaming.
• Strong knowledge of REST APIs and Microservices Architecture.
• Experience building and maintaining AI Platforms and deploying LLM-based applications.

Responsibilities

• Design, develop, and deploy enterprise-grade GenAI platform solutions.
• Build scalable LLM, RAG, and Agentic AI applications.
• Develop secure APIs and microservices for AI workloads.
• Automate deployments using CI/CD and DevSecOps best practices.
• Collaborate with cross-functional teams to deliver cloud-native AI solutions.
• Optimize platform performance, scalability, and reliability.

Skills

Python

Generative AI

LLMs

Prompt Engineering

RAG

Agentic AI

MCP

Data Engineering

Data Pipelines

REST APIs

Microservices

AI Platforms

LLM Deployments

AI Platform Performance

Kafka

Tools

Kubernetes

Docker

Kafka

Job description

Role & responsibilities

• Design, develop, and deploy enterprise-grade GenAI platform solutions.
• Build scalable LLM, RAG, and Agentic AI applications.
• Develop secure APIs and microservices for AI workloads.
• Automate deployments using CI/CD and DevSecOps best practices.
• Collaborate with cross-functional teams to deliver cloud-native AI solutions.
• Optimize platform performance, scalability, and reliability.

Preferred candidate profile

• Strong proficiency in Python
• Experience with Generative AI, LLMs, Prompt Engineering
• Hands-on experience with RAG (Retrieval-Augmented Generation) and Agentic AI
• Knowledge of Model Context Protocol (MCP)
• Strong Data Engineering fundamentals and data pipeline development
• Experience with Kubernetes, Docker, and Containerized Applications
• Cloud experience with AWS, Azure, or GCP
• CI/CD, DevSecOps, Infrastructure as Code, and automation
• Experience with Kafka/Event Streaming
• Strong knowledge of REST APIs and Microservices Architecture
• Experience building and maintaining AI Platforms and deploying LLM-based applications