We are looking for highly experienced professionals with 10 to 12 years of overall experience and strong expertise in Agentic AI, Enterprise GenAI solutions, and cloud-native AI deployments.

Required Skills :

- Strong proficiency in Python for AI/ML development and backend engineering

- Hands-on experience with LLMs and AI platforms such as GCP Vertex AI, Amazon Bedrock, Azure OpenAI, OpenAI-compatible APIs

- Proven experience in designing and implementing Agentic AI systems, autonomous workflows, and multi-agent orchestration

- Strong understanding of RAG Pipelines, Knowledge Graphs, Vector Databases (Pinecone, FAISS, Weaviate, ChromaDB, etc.)

- Experience with memory management in multi-agent systems and context retention strategies

- Expertise in API integrations, microservices architecture, and cloud-native deployments

- Hands-on experience with Azure-based AI deployments, monitoring, observability, and production support

- Strong understanding of CI/CD pipelines, DevOps practices, Docker, Kubernetes

- Ability to deliver measurable business impact through scalable enterprise AI solutions

Preferred Experience :

- Hands-on enterprise GenAI delivery in production environments

- Experience building intelligent assistants, copilots, workflow automation solutions

- Strong knowledge of prompt engineering, model evaluation, guardrails, and governance

- Exposure to LangChain, LangGraph, Semantic Kernel, AutoGen, CrewAI or similar frameworks

Client Interview Topics (Scenario Based) :

- AI Solution Deployment & Production Rollout

- Designing and Optimizing RAG Pipelines

- Multi-Model Agentic AI - Memory Management Strategies

- Agent-to-Agent Triggering / Workflow Orchestration

- Observability, Performance Monitoring & Cost Optimization