About the Role

We are looking for an AI Backend Engineer with 2+ years of experience in backend development and hands-on exposure to Generative AI, LLMs, RAG pipelines, and agentic AI systems.

The ideal candidate will be responsible for designing, developing, and deploying production-grade AI-powered backend systems and scalable microservices. You will work on enterprise-level AI solutions involving LLM orchestration, retrieval systems, AI agents, APIs, databases, and cloud deployments.

Key Responsibilities

- Design and develop production-grade backend systems using Python.
- Build and maintain RAG (Retrieval-Augmented Generation) pipelines and LLM-powered applications.
- Develop agentic AI workflows using frameworks such as LangChain, LangGraph, LlamaIndex, and MCP.
- Build scalable and high-performance APIs using Django and FastAPI.
- Develop and maintain microservices architecture using RabbitMQ, Redis, and other backend technologies.
- Integrate LLMs, vector databases, APIs, and other AI/ML components into production applications.
- Develop, train, and integrate machine learning models for business use cases such as churn prediction, classification, and forecasting.
- Work with ML algorithms such as XGBoost, Random Forest, and other relevant models.
- Containerize applications using Docker and manage production deployments.
- Deploy and maintain applications on AWS EC2 and Linux/RHEL environments.
- Implement application monitoring and observability using tools such as Prometheus.
- Optimize APIs and backend services for improved performance, scalability, and latency.
- Troubleshoot production issues and continuously improve system reliability and efficiency.
- Collaborate with AI/ML engineers, backend developers, product teams, and other stakeholders to deliver enterprise-grade AI solutions.

Required Skills




- 2+ years of skilled experience in Python backend development.
- Strong knowledge of Python, Django, and/or FastAPI.
- Hands-on experience building REST APIs and microservices.
- Practical experience with LLMs and Generative AI applications.
- Experience with RAG pipelines and vector search/retrieval systems.
- Experience with one or more of LangChain, LangGraph, LlamaIndex, or MCP.
- Good understanding of AI agents and agentic workflows.
- Experience with Redis and RabbitMQ or similar messaging/caching technologies.
- Hands-on experience with Docker and Linux/RHEL.
- Exposure to AWS, particularly EC2 and cloud-based deployments.
- Understanding of machine learning concepts and model development.
- Experience with ML algorithms such as XGBoost and Random Forest is preferred.
- Understanding of API performance, scalability, monitoring, and optimization.
- Strong debugging, problem-solving, and analytical skills.

Good to Have
- Experience working on enterprise-scale AI/LLM projects.
- Experience with telecom, customer analytics, or large-scale data platforms.
- Experience working with datasets containing millions of records.
- Knowledge of vector databases and embedding models.
- Experience with LLM evaluation, prompt engineering, and model optimization.
- Familiarity with CI/CD and production deployment practices.
- Experience with observability and monitoring tools such as Prometheus/Grafana.

What We’re Looking For
- Strong ownership of backend and AI systems from development to deployment.
- Ability to build reliable, scalable, and production-ready solutions.
- Strong understanding of both backend engineering and applied AI/ML.
- Ability to independently troubleshoot and optimize production systems.
- Passion for building practical GenAI and LLM-powered applications.
- Good communication and collaboration skills.

Pay: ₹300,000.00 - ₹500,000.00 per year

Work Location: In person

📌 AI Backend Engineer (Faridabad)
🏢 IKTARA DATA SCIENCE
📍 Faridabad