Artificial Intelligence Engineer

Photon; New York (NY); On-site; USD 120,000 - 150,000; Full time

Job summary

A leading technology firm is seeking a Generative AI Engineer to build and optimize production-ready AI applications. The role involves designing complex multi-agent systems and managing LLM deployments. Candidates should have strong Python skills and experience with GenAI applications, vector search, and monitoring in a production setting. This is an opportunity to work with cutting-edge technology and contribute to advanced AI workflows in a collaborative environment.

Qualifications

• Hands-on experience building and deploying GenAI applications in a production setting.
• Strong proficiency in Python and the modern AI library ecosystem.
• Familiarity with production-grade monitoring, API security, and CI/CD for ML.

Responsibilities

• Develop and orchestrate sophisticated AI workflows using LangGraph and multi-agent architectures.
• Integrate and swap diverse LLMs based on performance and cost requirements.
• Optimize GenAI workflows for latency, cost, and reliability.

Skills

GenAI application deployment

Python proficiency

Experience with vector search

Model fine-tuning techniques

Knowledge of CI/CD for ML

Tools

LangChain

LlamaIndex

PostgreSQL

Docker

FastAPI

Job description

We are seeking a Generative AI Engineer to build, optimize, and scale production-ready AI applications. You will design complex multi-agent systems, implement advanced RAG pipelines, and manage the deployment of both frontier and local LLMs. The ideal candidate blends deep machine learning expertise with modern software engineering practices.

Technical Stack

• LLMs: Gemini, OpenAI, Claude, Llama, and Local Model deployment.
• Frameworks: LangChain, LlamaIndex, and Hugging Face.
• Orchestration: LangGraph and Multi-Agent Systems (MAS).
• Development: Python, FastAPI, and Asynchronous Programming.
• RAG & Data: PostgreSQL, Vector Databases, and Advanced Retrieval strategies.
• ML/DL: PyTorch, TensorFlow, and Model Fine-tuning.
• Deployment: Docker, Production API management, and LLM monitoring.
• Tools: Prompt Engineering, Workflow Design, and GenAI Optimization.

Key Responsibilities

• Develop and orchestrate sophisticated AI workflows using LangGraph and multi-agent architectures.
• Build and maintain Advanced RAG systems utilizing LlamaIndex and vector databases for high-accuracy retrieval.
• Integrate and swap diverse LLMs (commercial and open-source) based on performance and cost requirements.
• Design and deploy high-performance, scalable backend services using FastAPI and Async Python.
• Fine-tune large language models (LLMs) using PyTorch/TensorFlow to improve domain-specific performance.
• Optimize GenAI workflows for latency, cost, and reliability using advanced prompt engineering and monitoring tools.
• Containerize and deploy AI services via Docker to production environments.

Required Qualifications

• Hands-on experience building and deploying GenAI applications in a production setting.
• Strong proficiency in Python and the modern AI library ecosystem (LangChain, LlamaIndex, etc.).
• Experience with vector search, embedding models, and advanced data retrieval patterns.
• Knowledge of model fine-tuning techniques and local LLM quantization/hosting.
• Familiarity with production-grade monitoring, API security, and CI/CD for ML.