Senior GenAI Engineer — LLMs, RAG & AI Agents

Luxoft; United States; Remote; USD 170,000 - 260,000; Full time

Job summary

Luxoft is seeking a senior software engineer to design and maintain an enterprise-scale Generative AI platform in the United States. You will build scalable Python APIs with FastAPI and FastMCP, integrate OpenAI GPT and Anthropic Claude, and develop RAG pipelines with Pinecone or Milvus to power candidate insights and workflow automation.

You will own architecture, deployment, monitoring, and CI/CD, mentor teammates, and collaborate with product and stakeholders to translate requirements into

Qualifications

• 7+ years of experience in software engineering.
• Proficiency in Python development and modern frameworks.
• Expertise with FastAPI and FastMCP for scalable APIs.
• Experience with OpenAI GPT and Anthropic Claude.
• Familiarity with vector databases Pinecone / Milvus and RAG.

Responsibilities

• Design, develop, and maintain scalable Python apps using FastAPI and FastMCP.
• Build production-grade REST APIs and AI-powered services with security and reliability.
• Develop AI solutions using LLMs such as OpenAI GPT and Anthropic Claude.
• Design AI Agents, Plugins, Skills, and MCP-based integrations to automate workflows.
• Build and optimize RAG pipelines with Pinecone or Milvus.
• Create prompt frameworks and context-management strategies.
• Own end-to-end AI solution lifecycle from architecture to production support.
• Collaborate with product managers, architects, and stakeholders to translate requirements.
• Implement monitoring, logging, observability, and performance improvements.
• Mentor team members and participate in design discussions.

Skills

Python

FastAPI

OpenAI GPT

Anthropic Claude

LangChain

RAG Architecture

AI Agents

GitHub

Monitoring

Tools

FastMCP

Pinecone

Milvus

Docker

Azure

AWS

CI/CD

VS Code

Job description

Luxoft is seeking a senior software engineer to design and maintain an enterprise-scale Generative AI platform in the United States. You will build scalable Python APIs with FastAPI and FastMCP, integrate OpenAI GPT and Anthropic Claude, and develop RAG pipelines with Pinecone or Milvus to power candidate insights and workflow automation.

You will own architecture, deployment, monitoring, and CI/CD, mentor teammates, and collaborate with product and stakeholders to translate requirements into