Our client is seeking an AI-focused Developer to design, build, and deploy production-grade Generative AI and Agentic AI solutions .

The role requires strong hands-on expertise in Python or TypeScript, Agentic AI, RAG, LLMs, LangChain/LangGraph, vector databases, APIs, and cloud AI platforms , with practical experience delivering real-world AI applications into production.

Candidates with only theoretical knowledge, training, certifications, or basic proof-of-concept exposure in Agentic AI will not be considered.

Key Responsibilities

• Build and deploy Generative AI and Agentic AI applications
• Develop scalable backend services using Python or TypeScript
• Design RAG pipelines, LLM workflows, and agentic architectures
• Build agents using tool calling, APIs, memory, planning, retrieval, and multi-step workflows
• Integrate REST APIs, GraphQL APIs, vector databases, and enterprise data sources
• Deploy AI applications on AWS, Azure, or GCP
• Monitor and optimize AI systems for accuracy, reliability, latency, scalability, and cost
• Implement Git, CI/CD, documentation, and production deployment workflows
• Collaborate with engineering, product, data, and business teams

Required Skills – Must Have

• Experience: 3+ years of overall relevant software / AI application development experience
• Generative AI / LLMs: 2+ years of hands-on experience building LLM-based applications
• Agentic AI: 1+ year of hands-on experience building and deploying real-world Agentic AI solutions. Proven experience with multi-step agent workflows, tool calling, API integration, memory, planning, reasoning, and autonomous execution
• Python: Strong proficiency in Python for backend and AI application development
• RAG: Strong understanding of Retrieval-Augmented Generation, embeddings, semantic search, vector retrieval, and contextual grounding
• LangChain / LangGraph: Hands-on experience with LLM orchestration and agent frameworks
• Vector Databases: Experience with Pinecone, ChromaDB, FAISS, Weaviate, or similar

Nice-to-Have Skills

• Multi-agent systems
• Advanced RAG architectures
• AutoGen, CrewAI, or Semantic Kernel
• Agent memory, planning, state management, and human-in-the-loop workflows
• LLM evaluation, observability, guardrails, and responsible AI
• Docker, Kubernetes, serverless, and cloud-native deployments
• LLM optimization for latency, reliability, token usage, and cost
• Fine-tuning, model selection, and AI application security

About YMinds.AI

YMinds.AI is a technology-focused talent solutions company helping organizations hire exceptional professionals across Engineering, AI/ML, Data, Cloud, Product, and Business functions.

Through our AI-powered talent platform, EmployAbility.AI, we enable faster access to verified and high-quality candidates through intelligent matching, expert screening, and a continuously refreshed talent network.

Keywords

Agentic AI Developer, Generative AI Engineer, LLM Developer, AI Agents, Python, TypeScript, RAG, LangChain, LangGraph, LlamaIndex, AutoGen, CrewAI, REST APIs, GraphQL, Microservices, Prompt Engineering, Tool Calling, Vector Databases, Pinecone, ChromaDB, FAISS, Weaviate, AWS Bedrock, SageMaker, Vertex AI, Azure OpenAI, CI/CD

Hashtags

AgenticAI #GenerativeAI #AIEngineer #LLMDeveloper #AIAgents #Python #TypeScript #RAG #LangChain #LangGraph #LlamaIndex #PromptEngineering #CloudAI #Hiring #TechJobs #YMindsAI