Senior AI Engineer

About the role

We are looking for a Senior AI Engineer to design and deliver production‑grade Retrieval‑Augmented Generation (RAG) pipelines and AI‑powered automation workflows. You will work closely with our engineering team to integrate large language models (LLMs) into web and mobile products for both client and internal projects.

Key responsibilities

• Design and build production‑grade RAG pipelines using vector databases, hybrid retrieval strategies, and reranking layers.
• Fine‑tune and evaluate large language models for domain‑specific use cases.
• Develop AI automation workflows with n8n, integrating LLMs, APIs, and external data sources.
• Collaborate with engineering to deploy AI features into web and mobile products.
• Use frameworks such as LangChain, TensorFlow, PyTorch, or equivalents to build scalable AI systems.
• Own model evaluation, performance monitoring, and iterative improvement of deployed AI systems.
• Contribute to AI architecture and tooling decisions across Lak‑Che’s product suite.
• Document AI systems clearly and maintain reproducible, version‑controlled pipelines.

Required profile

• Minimum 5 years of professional software or AI engineering experience.
• Strong, demonstrable proficiency in Python (primary language).
• Hands‑on experience building RAG pipelines in production.
• Experience with LLM fine‑tuning, dataset preparation, training, evaluation, and deployment.
• Proficiency with at least one major AI framework: LangChain, TensorFlow, PyTorch, or equivalent.
• Production‑level experience with n8n for AI workflow automation.
• Solid understanding of vector databases (Pinecone, Weaviate, ChromaDB, or similar).
• Strong grasp of prompt engineering, context window management, and LLM orchestration patterns.
• Verified AI project portfolio with references.

Required skills

• Python
• LangChain
• TensorFlow
• PyTorch
• n8n
• Pinecone
• Weaviate
• ChromaDB
• LLM fine‑tuning
• Prompt engineering
• FastAPI
• AWS Bedrock
• Google Vertex AI
• Azure OpenAI
• MLOps practices (model versioning, CI/CD for ML, monitoring)
• Data pipelines and ETL for AI training datasets

What we offer

• Hybrid work arrangement with on‑site and remote flexibility.
• Competitive compensation based on experience and impact.
• Opportunity to work on live, cutting‑edge AI products used by real users.
• Direct collaboration with founding leadership and the Lead Developer.
• Clear growth path toward an AI Lead or Head of AI role.