AI/ML Engineer
Location: [Remote / Hybrid / Bengaluru ]
Experience Level: Mid-Senior (8+ years total IT/engineering experience)
Key Responsibilities
- Design, build, and deploy enterprise-grade chatbots and conversational AI applications using RAG architecture to enable accurate, context-aware, and hallucination-reduced responses
- Develop end-to-end RAG pipelines including document ingestion, chunking, embedding generation, vector storage, hybrid/semantic retrieval, re-ranking, and generation augmentation
- Integrate Large Language Models (LLMs) (via Azure OpenAI or other providers) with retrieval systems and implement advanced techniques such as query rewriting, contextual compression, and evaluation metrics
- Architect and implement scalable AI/ML solutions on Microsoft Azure, leveraging services such as Azure OpenAI, Azure AI Search (for vector/hybrid search), Azure Machine Learning, Azure AI Services, Prompt Flow, and Azure Cosmos DB / Azure SQL
- Build and maintain production MLOps pipelines using Azure DevOps, MLflow, or equivalent tools for model versioning, CI/CD, monitoring, and automated retraining
- Collaborate with data engineers, product managers, and domain experts to translate business requirements into high-quality AI features
- Optimize AI systems for performance, cost, latency, and reliability in cloud environments
- Implement evaluation frameworks, A/B testing, and continuous improvement for conversational accuracy and user satisfaction
- Ensure secure, compliant, and ethical AI implementations (guardrails, PII handling, content filtering)
Required Qualifications & Experience
- 8+ years of overall software engineering / development experience
- 4+ years of hands-on experience with Microsoft Azure cloud platform (Azure PaaS services preferred)
- 2+ years of dedicated AI/ML engineering experience, with proven delivery of production AI/ML solutions
- Strong hands-on experience designing and implementing chatbots / conversational agents using RAG architecture
- Practical expertise in building RAG systems, including:
- Vector databases / vector search (Azure AI Search, FAISS, Pinecone, Weaviate, etc.)
- Embedding models and semantic search techniques
- Orchestration frameworks such as LangChain, LlamaIndex, Semantic Kernel, or Haystack
- Proficiency in Python (production-grade coding)
- Experience working with LLMs — prompt engineering, fine-tuning (nice to have), chaining, tool/function calling
- Familiarity with Azure AI ecosystem: Azure OpenAI, Azure Machine Learning, Azure Cognitive Services / AI Search, Bot Framework (advantage)
- Good understanding of MLOps practices and deployment patterns (Docker, Kubernetes, CI/CD)
Preferred / Nice-to-Have Skills
- Azure certifications (e.g., Azure AI Engineer Associate, Azure Data Scientist Associate)
- Experience with agentic AI / multi-agent systems
- Knowledge of classical ML + deep learning frameworks (PyTorch / TensorFlow)
- Exposure to evaluation tools (RAGAS, DeepEval) and observability for GenAI applications
- Previous work in enterprise environments (security, scalability, cost optimization)
What We Offer
- Opportunity to work on cutting-edge Generative AI and RAG-powered solutions
- Collaborative environment with focus on innovation and learning
- Competitive compensation and benefits