ML Engineer

Join Us for a Unique AI Writing Assistant Project!

Are you passionate about cutting-edge AI, large language models, and shaping the future of creative technology? Join 10Clouds as we develop a custom AI writing assistant for a renowned philosophical author. This is not your average AI project—your work will empower an award-winning writer to maintain their signature style, structure, and tone across entire manuscripts, with privacy and context memory at its core.

What makes this project special?

You’ll help build a fully private, fine-tuned AI that mimics a specific author’s voice—no stylistic drift allowed!

Work closely with a highly technical, multidisciplinary team at 10Clouds, a leader in AI product development.

Deliver a real, production-ready solution with a deep focus on privacy, autonomy, and quality.

The stack includes cutting-edge LLMs (LLaMA 3, Mixtral), Retrieval-Augmented Generation (RAG), FastAPI, Qdrant/Weaviate vector search, and a custom web editor for writers.

Your Responsibilities:

Analyze client requirements and help design the optimal system architecture.

Prepare and process text data for model fine-tuning.

Fine-tune large language models (e.g., LLaMA 3, Mixtral 8x7B) using LoRA or similar methods.

Develop a robust RESTful API for text generation and session management.

Implement intelligent knowledge retrieval/search using RAG techniques.

Build a responsive, user-friendly web interface for long-form creative writing.

Integrate document context/version management features.

Deploy and monitor infrastructure on cloud (AWS/GCP) with Docker and FastAPI.

Test, quality assure, and optimize the system for tone consistency and usability.

Maintain documentation and support seamless project handover to the client.

Requirements:

Hands-on experience with large language models (preferably LLaMA or Mixtral).

Practical knowledge of fine-tuning techniques (LoRA, transfer learning).

Advanced Python skills; experience with FastAPI, Docker, and CI/CD.

Familiarity with vector databases (Qdrant, Weaviate) and RAG algorithms.

Proven background in API development and microservice architecture.

Proficiency in deploying cloud solutions (AWS or GCP).

Experience with web development tools (React/Vue, responsive design).

Independence, Strong Communication Skills, And Client-facing Experience.

Bonus: QA/testing in AI, UX/UI design experience.

If you’re ready to work in a highly collaborative team, build deeply personalized AI, and shape the way authors harness next-generation assistant technology, we want to hear from you!

Apply now and help us push the boundaries of what's possible in AI-powered writing!