AI Backend Engineer – LLM Systems & Orchestration ( 5+ Years)

Title: Senior AI Backend Engineer - LLM Infrastructure

Location: Jaipur

Experience: 4-8 years

Reports To: Principal AI Architect

Role Overview

We are building scalable AI infrastructure for enterprise-grade LLM applications.

We are looking for a strong backend engineer who has experience integrating LLM systems into production environments and building orchestration services around them.

This role will focus on service-layer architecture, API design, performance optimization, and secure deployment of AI systems.

Key Responsibilities

• Build scalable microservices around LLM applications
• Integrate RAG pipelines into backend systems
• Develop APIs for AI orchestration layers
• Implement streaming and async LLM workflows
• Build logging and observability pipelines for AI responses
• Optimize performance and latency of LLM-based systems
• Implement secure access control and rate limiting
• Work closely with AI Architect on evaluation integration
• Containerize and deploy AI services using Docker/Kubernetes

Required Qualifications

• 4+ years backend engineering experience
• Strong Python (FastAPI preferred)
• Experience integrating OpenAI / Anthropic / open-source LLM APIs
• Familiarity with vector databases
• Experience with REST APIs and event-driven systems
• Experience with Docker and cloud deployment
• Strong understanding of async processing

Must Have Built

Candidates must demonstrate:

• LLM API integration in production
• Backend service around LLMs (not just scripts)
• Deployment of AI services to cloud
• Logging and monitoring setup
• Performance optimization experience

Nice to Have

• Experience with Kafka / message queues
• Experience with CI/CD for ML services
• Experience with embeddings and search tuning
• Familiarity with OpenTelemetry