U

Agentic AI Engineer / Applied AI Engineer

United IT
2 hours ago
Full-time
On-site
East New York, New York, United States
Agentic Ai Engineer / Applied Ai Engineer

We are seeking a highly skilled Agentic Ai Engineer / Applied Ai Engineer to design, develop, and deploy next-generation Ai systems. This role focuses on leveraging large language models (Llms), autonomous agents, retrieval systems, and intelligent workflows to solve complex enterprise challenges. At the 409 level (Senior Software Engineer), this position requires strong hands-on engineering expertise, sound software architecture skills, and the ability to independently lead the delivery of scalable Ai-powered products and platforms. The ideal candidate combines solid software engineering fundamentals with applied Ai/Ml experience and thrives in fast-paced, innovation-driven environments. Key Responsibilities

Ai Agentic Systems Development Applied Ai Engineering Software Engineering and Platform Development Leadership and Collaboration Design and implement intelligent Ai agents capable of reasoning, planning, tool usage, memory management, and multi-step workflow execution. Build production-grade Llm applications using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar orchestration platforms. Develop retrieval-augmented generation (Rag) pipelines that integrate vector databases with enterprise knowledge systems. Create autonomous workflows that connect APIs, tools, databases, and enterprise services. Fine-tune, evaluate, and optimize Llms and generative Ai systems for enterprise use cases. Develop prompt engineering strategies, evaluation pipelines, guardrails, and Ai safety mechanisms. Implement Ai observability, monitoring, hallucination detection, and performance optimization solutions. Work with structured and unstructured data pipelines for Ai model consumption. Build scalable backend services and APIs using Python, Java, Node.js, or Go. Design cloud-native Ai architectures on platforms such as Aws, Azure, or Gcp. Develop microservices and containerized applications using Docker and Kubernetes. Implement Ci/Cd pipelines, testing frameworks, and infrastructure-as-code practices. Lead technical design discussions and architecture reviews. Mentor junior engineers and guide Ai engineering best practices. Collaborate with product managers, data scientists, architects, and business stakeholders to deliver Ai-driven solutions. Drive technical innovation and contribute to enterprise Ai strategy. Required Qualifications

Bachelor's or Master's degree in Computer Science, Engineering, Ai/Ml, or a related field. At least 5 years of software engineering experience. At least 2 years of hands-on experience building generative Ai or Llm-based applications. Strong programming skills in Python and at least one additional language such as Java, Go, or JavaScript/TypeScript. Experience with Llm APIs such as OpenAI, Anthropic, or open-source models. Hands-on experience with vector databases such as Pinecone, Weaviate, FAISS, or ChromaDB. Strong understanding of Rag architectures, semantic search, REST APIs, distributed systems, and scalable backend design. Experience with cloud platforms including Aws, Microsoft Azure, or Google Cloud Platform. Strong understanding of software design patterns, system scalability, and observability. Preferred Qualifications

Experience with multi-agent orchestration systems. Familiarity with Ai governance, responsible Ai, and enterprise security standards. Experience deploying Ai systems in healthcare, retail, insurance, or pharmacy domains. Knowledge of reinforcement learning, model fine-tuning, or evaluation frameworks. Contributions to open-source Ai projects or published technical research. Technical Skills

Programming and Frameworks Languages: Python, Java, TypeScript, Go Frameworks and platforms: FastAPI, Flask, Spring Boot, Node.js Agent orchestration: LangChain, LangGraph, CrewAI, AutoGen Ai/Ml tooling: PyTorch, TensorFlow, Hugging Face Ai and Data Technologies Llms and generative Ai Retrieval-augmented generation (Rag) Vector databases Prompt engineering Ai evaluation frameworks Nlp and semantic search Cloud and DevOps Cloud platforms: Aws, Azure, Gcp Containerization and orchestration: Docker, Kubernetes Infrastructure as code: Terraform Ci/Cd tools: GitHub Actions, Jenkins Monitoring and observability tools Senior-Level Expectations (409)

Independently own large technical initiatives end to end. Make architectural decisions with long-term scalability in mind. Drive engineering excellence and operational maturity. Influence technical direction across teams. Balance rapid experimentation with production-grade engineering discipline. Nice-to-Have Experience

Healthcare or pharmacy technology experience. Experience building conversational Ai platforms or enterprise copilots. Knowledge of Hipaa compliance and regulated Ai environments. Exposure to graph-based orchestration and workflow engines. Mandatory Skills:

Ai implementation infrastructure, vector databases, Rag, Docker, Gcp DevOps, LangChain, Mlops, and Python.