remote
AI Engineer l Generative AI - MyAdvice
AI Engineer
Design and deploy scalable Generative AI solutions, building LLM‑powered pipelines, AI agents, and RAG systems using Python, LangChain, vector databases, and model fine‑tuning techniques.
About the role
Key Responsibilities
- Architect, develop, and launch production‑grade Generative AI pipelines powered by large language models such as GPT, LLaMA, and Gemini.
- Implement Retrieval‑Augmented Generation (RAG) workflows using vector databases and frameworks like LangChain to enable context‑aware responses.
- Fine‑tune and optimize foundation models for domain‑specific tasks, ensuring high accuracy, low latency, and cost‑effective inference.
- Collaborate with product, data, and engineering teams to translate business problems into AI‑driven solutions and integrate them into existing services.
- Monitor, troubleshoot, and continuously improve deployed AI systems, applying best practices for scalability, reliability, and security.
Requirements
- Strong hands‑on experience with Python and deep‑learning libraries such as PyTorch or TensorFlow.
- Proven expertise in building and deploying LLM‑based applications, including prompt engineering, fine‑tuning, and inference optimization.
- Experience with LangChain, vector stores (e.g., Pinecone, Weaviate, FAISS), and Retrieval‑Augmented Generation techniques.
- Solid understanding of model evaluation, performance tuning, and production monitoring for AI services.
- Ability to work cross‑functionally, communicate technical concepts clearly, and deliver end‑to‑end AI solutions on schedule.
Skills
pythonlangchainpytorch