Generative AI Engineer

The Phoenix Group; New York (NY); On-site; USD 130,000 - 170,000; Full time

Job summary

The Phoenix Group seeks an experienced AI Engineer to design and implement agentic AI applications that can reason, plan, and execute tasks across enterprise systems. You will build multi-agent architectures for complex workflows and develop tool-calling capabilities to integrate with APIs, databases, and internal services.

You will optimize RAG pipelines, embeddings, and contextual retrieval, and work with LangGraph, LangChain, Semantic Kernel, AutoGen, and other frameworks.

Qualifications

• Strong Python development fundamentals.
• Hands-on experience building Generative AI or LLM-powered applications.
• Experience creating agentic workflows beyond chatbots.
• Experience with LLM APIs, function/tool calling, structured outputs, and model orchestration.
• Understanding of RAG, embeddings, vector databases, and context management.
• Experience integrating AI apps with APIs, databases, SaaS, or enterprise systems.

Responsibilities

• Design and build agentic AI applications that can reason, plan, execute tasks, and interact with external tools and systems.
• Develop single-agent and multi-agent architectures for complex business workflows.
• Build tool-calling capabilities to interact with APIs, databases, and internal services.
• Develop and optimize RAG pipelines, vector search, embeddings, and contextual retrieval.
• Integrate LLMs from platforms such as OpenAI, Anthropic, Google, and open-source providers.
• Create orchestration workflows using LangGraph, LangChain, Semantic Kernel, AutoGen, or similar technologies.
• Implement memory, state management, guardrails, and human-in-the-loop controls.
• Develop evaluation frameworks to measure agent accuracy, reliability, and latency.
• Deploy, monitor, and improve AI applications in production environments.
• Collaborate with engineering, data, security, product, and business teams to identify automation opportunities.

Skills

Python

Generative AI

LLM-powered apps

Agent workflows

LLM APIs

RAG/embeddings

Vector databases

Model orchestration

Azure/AWS/GCP

Security & guardrails

Tools

LangGraph

LangChain

Semantic Kernel

AutoGen

CrewAI

Job description

• Design and build agentic AI applications that can reason, plan, execute tasks, and interact with external tools and systems.
• Develop single-agent and multi-agent architectures for complex business workflows.
• Build tool-calling capabilities that allow agents to interact with APIs, databases, enterprise applications, and internal services.
• Develop and optimize RAG pipelines, vector search, embeddings, and contextual retrieval.
• Integrate LLMs from platforms such as OpenAI, Anthropic, Google, and open-source providers.
• Build orchestration workflows using LangGraph, LangChain, Semantic Kernel, AutoGen, or similar technologies.
• Implement memory, state management, guardrails, human-in-the-loop controls, and structured outputs.
• Develop evaluation frameworks to measure agent accuracy, reliability, latency, and task completion.
• Deploy, monitor, and improve AI applications in production environments.
• Partner with engineering, data, security, product, and business teams to identify opportunities for agent-driven automation.

Qualifications

• Strong Python development experience and software engineering fundamentals.
• Hands-on experience developing Generative AI or LLM-powered applications.
• Experience building AI agents or agentic workflows, beyond standalone chatbots or prompt-based applications.
• Experience with LLM APIs, function/tool calling, structured outputs, and model orchestration.
• Understanding of RAG, embeddings, vector databases, semantic search, and context management.
• Experience integrating AI applications with APIs, databases, SaaS platforms, or enterprise systems.
• Familiarity with agent frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI, or comparable technologies.
• Experience deploying AI applications in Azure, AWS, or GCP.
• Understanding of AI evaluation, observability, security, and guardrails.

Preferred

• Experience with Model Context Protocol (MCP).
• Experience building agents that automate end-to-end business processes.
• Knowledge of LLMOps/MLOps and production monitoring.
• Experience with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, or pgvector.
• Experience working with enterprise data, security, permissions, and identity controls.