Technology Architect | Cloud Platform | Google Cloud - Architecture

Key Responsibilities

• Design and implement Generative AI models for text, image, or multimodal applications.
• Develop prompt engineering strategies and embedding-based retrieval systems.
• Integrate Gen AI capabilities into web applications and enterprise workflows.
• Build agentic AI applications with context engineering and MCP tools.

Required Skills & Qualifications

• 7+ years of hands-on experience in AI, Data science, ML, GEN AI.
• 2 years of strong hands-on experience in Agentic AI, VLLM’s, GEN AI, Lang Chain, Lang Graph, RAG, LLM OPS and AI Services in GCP and Azure.
• Strong hands-on experience designing and deploying Retrieval-Augmented Generation (RAG) pipelines.
• Extensive experience with LangChain, LangGraph, and agentic AI patterns including routing, memory, multi-agent orchestration, guardrails, and failure recovery.
• Experience in Cloud-native engineering across AWS (SageMaker, Lambda, ECS/Fargate, S3, API Gateway, Step Functions) and GCP (Vertex AI) for scalable AI delivery.
• Experience in Developing microservices and API development using FastAPI, REST APIs, Pydantic/JSON schemas, Docker, and Kubernetes for low-latency serving.
• Strong Hands-on experience with vector databases and semantic search technologies including Pinecone, FAISS, ChromaDB, and embedding lifecycle management.
• Strong proficiency in Python and AI/ML frameworks (PyTorch, TensorFlow).
• Hands on experience using session and memory for building multi-agent systems along with using MCP tools.
• Hands-on experience with LLMs, transformers, and Hugging Face ecosystem.
• Knowledge and experience with vector databases and RAG technique for semantic search.
• Familiarity with cloud AI services (AWS SageMaker, Azure OpenAI, GCP Vertex AI).
• Understanding of MLOps practices for scalable AI deployment.
• Strong experience in working with LLM fine-tuning with LoRA, QLoRA, PEFT.
• Strong experience in Architected advanced RAG systems using Pinecone, FAISS, Weaviate, Chroma, hybrid retrieval, and custom embeddings.
• Strong experience in Designing end-to-end LLMOps/MLOps pipelines using MLflow, DVC, SageMaker Pipelines, Vertex AI Pipelines, and GitHub Actions.
• Experience in using cloud-native AI systems on AWS (SageMaker, Lambda, EKS, EC2, Step Functions, S3, Glue) and GCP Vertex AI, supporting high-volume inference and secure enterprise operations.
• Experience in developing multi-agent orchestration workflows using LangGraph and CrewAI for tool-calling, validation agents, automated reasoning, and workflow supervision.