DevJobs

Generative AI Engineer

Overview
Skills
  • Python Python
  • Linux Linux
  • RESTful API RESTful API
  • CI/CD CI/CD
  • Git Git
  • Docker Docker
  • LLM
  • vLLM
  • Vector Database
  • Backend
  • RAG
  • Ollama
  • llama.cpp
  • Hugging Face
  • GPU
  • CUDA
  • Generative AI
  • Embeddings
  • Claude Team
  • Prompt Engineering
  • Claude Code
  • Quantization
  • Tool Calling
  • Fine-Tuning

About the Role

We are looking for an AI Developer & Implementation Engineer to join our team and take part in the development, implementation, and maintenance of AI and Generative AI solutions, including in secure, isolated On-Premise environments.

The role includes deploying and operating local AI models, developing RAG solutions and AI Agents, integrating AI capabilities with enterprise systems, and leveraging AI-powered development tools such as Claude Code and Claude Team, in accordance with the organization's information security policies.

Key Responsibilities

  • Develop and implement AI and LLM solutions, including in On-Premise environments.
  • Deploy and operate GPU-based local AI models.
  • Develop RAG solutions, AI Agents, and enterprise search engines.
  • Install and deploy models using Ollama, vLLM, llama.cpp, Hugging Face, or similar tools.
  • Use Claude Code for code generation, code analysis, refactoring, testing, documentation, and development process automation.
  • Use Claude Team for knowledge sharing, collaboration, document analysis, and supporting development and engineering processes.
  • Adapt and optimize models using Prompt Engineering, Tool Calling, Quantization, and Fine-Tuning.
  • Participate in processes for onboarding, scanning, transferring, and deploying models and packages into isolated environments.
  • Monitor response times, accuracy, CPU/GPU utilization, memory consumption, and computational costs.

Requirements

  • Proven experience in Python software development.
  • Experience developing Backend services and REST APIs.
  • Hands-on experience working with LLMs and Generative AI solutions.
  • Experience deploying and operating local models using Ollama, vLLM, llama.cpp, or similar solutions.
  • Experience working with Hugging Face and open-source models.
  • Experience developing RAG solutions, Embeddings, and Vector Databases.
  • Experience with Linux and Docker.
  • Familiarity with GPU servers, CUDA, and compute resource management.
  • Experience integrating AI solutions with enterprise systems and internal data sources.
  • Experience with Git and CI/CD processes.
  • Experience using Claude Code or similar AI-powered software development tools.
  • Ability to work in secure, communication-restricted, or air-gapped environments.


Omnisys