AI Integration Engineer

Description :

Role : AI Integration Engineer (Backend / GenAI)

Location : Pune (Hybrid - 2 Days WFO)

Experience : 5 - 8 Years

Shift : 2 : 00 PM - 11 : 00 PM IST

About the Role :

We are hiring an AI Integration Engineer to build and scale AI-powered backend systems. The role involves integrating LLMs, NLP, and ML models into production applications and designing scalable APIs and services.

Key Responsibilities :

- Integrate AI/ML models (LLMs, NLP, embeddings) into applications

- Build REST APIs & microservices for AI-driven features

- Work with OpenAI / Azure OpenAI / Google AI APIs

- Deploy AI models into production with scalability & low latency

- Design data pipelines for AI model consumption

- Optimize performance, cost, and reliability of AI systems

- Collaborate with ML engineers & product teams

- Troubleshoot and improve AI integrations

Tech Stack (Must Have) :

- Backend : Node.js / Python / Java / Go

- APIs : REST, Microservices Architecture

- Cloud : AWS / Azure / GCP

- Databases : SQL / NoSQL

- Containers : Docker, CI/CD pipelines

Good to Have :

- LangChain / LlamaIndex / RAG pipelines

- Vector DBs : Pinecone / FAISS / Weaviate

- Messaging : Kafka / RabbitMQ

- Experience building GenAI products

What Were Looking For :

- 5+ years in backend/full-stack development

- Hands-on experience integrating AI/ML APIs or models

- Strong system design and debugging skills

- Experience with production-scale systems

Why Join Us :

- Work on real-world GenAI applications

- High ownership & fast-paced environment

- Opportunity to build scalable AI systems from scratch