Senior AI Engineer (Backend & AI Systems)
Explicitly requires vibe coding skills; role centers on AI-augmented development with an AI assistant to direct, review, and integrate generated code.
About the Role
Senior AI Engineer to design and build core backend and AI systems for a modular, gRPC-based orchestration platform, focusing on high-performance Python services, LLM integration, and scalable data persistence using relational and vector databases. The role uses an AI-augmented "Vibe Coding" workflow to direct AI-generated code, perform expert review, and rapidly iterate on architecture while collaborating closely with the lead architect.
Job Description
Role
Join a small founding team to develop the core backend and AI capabilities of a modular AI platform. The position focuses on designing high-performance Python services, implementing gRPC-based APIs for orchestration, integrating Large Language Models, and building scalable data persistence and ingestion pipelines using relational and vector databases.
Key Responsibilities
- Build and guide AI-augmented development of modular, high-performance Python backend services.
- Design, implement, and evolve gRPC-based APIs for orchestrator-to-tool communication.
- Integrate and orchestrate LLMs and third-party LLM APIs to enable tool selection, reasoning, and complex workflows.
- Architect and manage data persistence strategies combining PostgreSQL and vector databases (e.g., ChromaDB).
- Develop and optimize data ingestion and processing pipelines to enrich the AI knowledge base.
- Collaborate with the Lead Architect on core architecture, technical decisions, and platform direction.
- Critically review and integrate AI-generated code for correctness, efficiency, and standards compliance.
Requirements
- 5+ years professional experience building complex, scalable backend systems.
- Expert-level Python proficiency with strong object-oriented design and concurrency knowledge.
- Strong experience designing and building APIs; gRPC experience is a significant advantage. REST/FastAPI experience valued.
- Solid experience with PostgreSQL (or similar relational DBs) and familiarity with ORMs like SQLAlchemy.
- Practical understanding of vector databases (e.g., ChromaDB, Milvus) and their use in AI applications such as RAG.
- Hands-on experience with Docker for building, shipping, and running applications.
- Experience integrating with third-party LLM APIs and familiarity with concepts like tool calling and prompt engineering.
- Ability to understand, review, and integrate complex codebases, including AI-generated code.
Bonus (Highly Desirable)
- Demonstrated aptitude for AI-augmented workflows (“Vibe Coding”).
- Deep, hands-on experience building production gRPC ecosystems.
- Experience building end-to-end Retrieval-Augmented Generation (RAG) systems.
- Background in infrastructure automation, DevOps, or systems engineering.
Technical environment
- Primary languages, tools and platforms: Python, gRPC, PostgreSQL, ChromaDB, Milvus, SQLAlchemy, Docker, FastAPI, NVIDIA NIM, LLM APIs.
What We Offer
- Ground-floor impact on a cutting-edge AI product and close collaboration with the project architect.
- High degree of autonomy and flexibility in working hours.
- Option for remote work and a flexible work environment focused on results.