About the Opportunity
A fast-scaling AI-first technology firm operating at the intersection of enterprise automation and generative intelligence, we build production-grade AI systems that drive decision intelligence, autonomous workflow orchestration, and human-AI collaboration for Fortune 500 clients. Our engineers ship scalable, responsible, and interpretable AI solutions—leveraging LLMs, RAG, and multi-agent frameworks—deployed across hybrid cloud environments.

Role & Responsibilities

- Architect and deploy end-to-end AI systems—from data preprocessing to model serving—that scale to enterprise SLAs and real-time inference demands.
- Design and optimize RAG pipelines and multi-agent architectures using LangChain, LlamaIndex, or equivalent frameworks for domain-specific knowledge extraction.
- Integrate AI models into production services using FastAPI/Flask, containerize with Docker, and orchestrate via Kubernetes on AWS/Azure/GCP.




- Collaborate with product and data science teams to define model evaluation metrics, drift detection, and human-in-the-loop feedback loops.
- Implement prompt engineering, chain-of-thought orchestration, and output parsing strategies to improve accuracy and reliability of LLM responses.
- Lead AI governance initiatives—model versioning, audit trails, cost monitoring, and explainability tooling—to ensure compliance and reproducibility.

Skills & Qualifications

- Must-Have
- LangChain
- LlamaIndex
- FastAPI
- Docker
- Kubernetes
- AWS
- LLM
- Python
- Preferred
- MLflow
- Argilla
- Ray

Benefits & Culture Highlights

- Hybrid work model with adaptable office days and remote flexibility across India.
- Access to cutting-edge research and open-source tools with dedicated time for innovation sprints.
- Performance-driven culture with annual learning stipends and certification support.

📌 Senior AI Engineer (Hyderabad)
🏢 Granular Tek
📍 Hyderabad