Agentic AI Engineer

Position: Agentic AI Engineer

Location: : NYC , NY(Onsite)

Job type: Fulltime

Skills- Gen ai , Rag , python

Key Responsibilities

• Design and develop autonomous AI agents and multi-agent systems using LLMs.
• Build agentic workflows involving reasoning, planning, memory, tool calling, and task execution.
• Develop applications using LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or similar agent frameworks.
• Integrate LLMs such as OpenAI, Anthropic Claude, Google Gemini, Llama, and Mistral into enterprise applications.
• Build RAG (Retrieval-Augmented Generation) pipelines using embeddings, vector databases, document processing, and semantic search.
• Develop agent tools and integrations using REST APIs, GraphQL, MCP, SDKs, databases, enterprise applications, and third-party services.
• Implement short-term and long-term agent memory, context management, and state persistence.
• Develop intelligent workflows for decision-making, task decomposition, planning, and autonomous execution.
• Design and implement prompt engineering, structured outputs, function/tool calling, and context engineering.
• Build and optimize vector search solutions using Pinecone, Weaviate, Milvus, Chroma, FAISS, or pgvector.
• Develop scalable AI services and APIs using Python, FastAPI, Flask, or similar technologies.
• Deploy AI/ML workloads on AWS, Azure, or GCP.
• Implement production-grade CI/CD, containerization, monitoring, logging, and observability for AI applications.
• Evaluate and improve agent performance using LLM evaluation frameworks, automated testing, tracing, and monitoring.
• Implement responsible AI practices including security, access control, guardrails, hallucination mitigation, and data privacy.
• Collaborate with software engineers, data scientists, architects, and business stakeholders to convert business requirements into AI-driven solutions.

Required Skills

• Strong programming experience with Python.
• Hands-on experience building Agentic AI / AI Agent applications.
• Strong understanding of LLMs, Generative AI, NLP, and Transformer architectures.
• Experience with LangChain and/or LangGraph.
• Experience with RAG, embeddings, semantic search, and vector databases.
• Strong knowledge of prompt engineering and LLM orchestration.
• Experience with function calling, tool calling, APIs, and agent workflows.
• Experience with OpenAI, Anthropic, Gemini, Azure OpenAI, AWS Bedrock, or similar LLM platforms.
• Experience developing REST APIs and microservices.
• Experience with Git, Docker, Kubernetes, and CI/CD.
• Strong SQL and database knowledge.
• Experience with at least one major cloud platform: AWS, Azure, or GCP .