About The Opportunity
A fast-scaling tech innovator in the Enterprise AI & Cloud Engineering space, we build and deploy production-grade Generative AI solutions powered by large language models (LLMs), Retrieval-Augmented Generation (RAG), and cloud-native Python stacks on Microsoft Azure. Our team ships scalable, secure, and low-latency AI services that drive intelligent automation, conversational experiences, and decision intelligence for global clients—directly from Hyderabad.
Role & Responsibilities
- Design, build, and deploy end-to-end GenAI pipelines—from data ingestion and vector DB integration to RAG orchestration and LLM inference on Azure.
- Develop Python-based backend services integrating LangChain, FAISS/Chroma, and OpenAI/Azure OpenAI APIs for enterprise-grade AI workflows.
- Optimize and scale LLM inference pipelines using Azure Kubernetes Service (AKS), Azure Functions, or VMs to ensure low-latency, high-throughput production delivery.
- Implement and maintain RAG architecture patterns with hybrid search, reranking, and context-aware prompt engineering for domain-specific accuracy.
- Collaborate with data scientists to evaluate model performance, reduce hallucination, and embed guardrails, caching, and observability into AI services.
- Own CI/CD, monitoring (Azure Monitor / Grafana), and auto-scaling configurations to ensure service reliability, performance, and cost-efficiency.
Skills & Qualifications
Must-Have
- Python
- Azure OpenAI Service
- LangChain
- RAG Architecture
- Vector Databases (FAISS, Chroma, Pinecone)
- Azure Kubernetes Service (AKS)
- CI/CD (Azure DevOps / GitHub Actions)
- LLM fine-tuning or prompt engineering
Preferred
- Experience with Azure AI Studio or Azure Machine Learning
- Familiarity with LlamaIndex or Haystack frameworks
- Knowledge of MLOps best practices or MLflow
Benefits & Culture Highlights
- Work onsite in Hyderabad with top-tier AI infrastructure and direct mentorship from LLM architecture leads.
- Fast-track exposure to client deployments in BFSI, healthcare, and logistics sectors using cutting-edge Azure AI tools.
- Opportunity to contribute to open-source GenAI tooling and publish technical blogs as part of company-wide knowledge sharing.
Skills: genai,python,azure
