Back
Mid-level, in-demand GenAI skillset in a Mumbai role yields high applicant density and competition.
Role requires specialized LLM, RAG, and agentic engineering skills, making cross-industry transfers limited.
Explicit 5+ years and mandatory LLM, RAG, LangChain and production experience enforce strict shortlisting.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design and deploy autonomous AI agents and multi-step business workflow automations on the Amethyst platform using AWS SDK, LangChain, and cloud services.
Integrate advanced agentic reasoning and tool-calling capabilities with corporate knowledge bases, supporting APIs, databases, web search, and UI automation.
Manage persistent memory and state for long-running asynchronous agent workflows in distributed containerized or serverless environments, optimizing performance via prompt engineering and benchmarking.
5+ years of professional experience, specifically in Mumbai location.
Strong proficiency in Python and machine learning/NLP libraries.
Hands-on production experience with LLM orchestration frameworks (LangChain, LangGraph, LlamaIndex); AWS agentic development preferred.
Proven experience building production-grade Retrieval-Augmented Generation (RAG) architectures and working with vector databases; deep understanding of API development and tool/function-calling with commercial and open-source LLMs (OpenAI, Anthropic, Mistral, Llama).
Experienced in bridging state-of-the-art LLM research with scalable, production-grade AI applications focused on autonomous agents.
Technically adept at building resilient, self-correcting AI systems managing complex workflows and persistent states across distributed cloud environments.
Comfortable working with multiple AI frameworks and enterprise cloud services (especially AWS), with a focus on dynamic agent-driven architectures and robust error handling.