GenAI/Python Engineer: Scalable AI & LLM Orchestration

Photon; New York (NY); On-site; USD 150,000 - 210,000; Full time

Job summary

Photon is seeking an experienced GenAI/Python Developer to design, build, and deploy production-grade Generative AI applications and intelligent agent-based solutions. You will design, develop, and orchestrate sophisticated GenAI workflows using LangGraph, LangChain, and multi-agent architectures, and build robust RAG systems with LlamaIndex and vector databases.

The role requires hands-on experience with OpenAI, Anthropic, Llama, Mistral models, back-end APIs in Python, FastAPI, and

Qualifications

• Experience building GenAI applications and production-grade systems.
• Strong Python development and API design with FastAPI.
• Experience with retrieval-augmented generation and vector databases.
• Experience with multiple LLMs (OpenAI, Anthropic, etc.) and cost-aware selection.
• Ability to optimize latency and cost for production AI workloads.

Responsibilities

• Design, develop, and orchestrate GenAI workflows using LangGraph, LangChain, and multi-agent architectures.
• Build and maintain RAG solutions with LlamaIndex and vector databases.
• Create retrieval pipelines to improve LLM response accuracy and relevance.
• Evaluate and integrate OpenAI, Anthropic, Llama, Mistral models based on performance and cost.
• Develop scalable backend services and APIs using Python and FastAPI.

Skills

Python

GenAI design

LLM integration

Multi-agent architectures

Prompt engineering

Performance optimization

Tools

LangGraph

LangChain

LlamaIndex

Vector databases

PyTorch

TensorFlow

Hugging Face

LoRA

QLoRA

LangSmith

Langfuse

Docker

CI/CD

FastAPI

AWS

Azure

GCP

Job description

Photon is seeking an experienced GenAI/Python Developer to design, build, and deploy production-grade Generative AI applications and intelligent agent-based solutions. You will design, develop, and orchestrate sophisticated GenAI workflows using LangGraph, LangChain, and multi-agent architectures, and build robust RAG systems with LlamaIndex and vector databases.

The role requires hands-on experience with OpenAI, Anthropic, Llama, Mistral models, back-end APIs in Python, FastAPI, and