Backend Engineer (AI-heavy)

enter; Bengaluru; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

enter is seeking a backend engineer to design and build scalable AI-powered systems in Bengaluru. You will bridge application logic with machine learning infrastructure, delivering robust services that power AI features.

You will own architecture, implementation, and deployment of services integrating large language models and AI pipelines into production environments, with emphasis on security and scalability.

Qualifications

• Experience in building REST APIs and backend services at scale.
• Strong understanding of databases and system design patterns.
• Familiarity with LLM APIs, RAG pipelines, vector databases, and AI integrations.

Responsibilities

• Develop REST APIs and microservices to handle requests and orchestrate AI operations.
• Connect to LLM APIs and manage interactions with language models.
• Create and optimize retrieval-augmented generation (RAG) pipelines.
• Implement vector database integrations for embeddings and semantic search.
• Design database schemas, queries, and caching for AI workloads.
• Build authentication and authorization layers to protect data and API access.

Skills

Python

Java

Node.js

Tools

REST APIs

Microservices

LLM APIs

Vector databases

Caching

Auth/Authorization

Job description

Batch: 2019/2020/2021/2022/2023/2024.

About the role:

• You will design and build backend systems that power AI-driven features and services
• Your work bridges application logic and machine learning infrastructure, ensuring scalable foundations for AI workloads
• You'll own the architecture, implementation, and deployment of services that integrate large language models and AI pipelines into production environments

What you'll work on:

• Developing REST APIs and microservices that handle requests, orchestrate AI operations, and return results to clients
• Building systems that connect to LLM APIs and manage interactions with language models
• Creating and optimizing retrieval-augmented generation (RAG) pipelines that combine data retrieval with AI inference
• Implementing vector database integrations to store and query embeddings for semantic search and similarity matching
• Designing database schemas, query patterns, and caching strategies that support both traditional and AI workloads
• Engineering authentication and authorization layers that protect sensitive data and control API access

What we're looking for:

• Strong command of Python, Java, Node.js, or equivalent backend programming languages
• Proven experience building REST APIs, backend services, and microservices at scale
• Solid understanding of databases, system design principles, and architectural patterns
• Familiarity with LLM APIs, RAG pipelines, vector databases, and AI integrations