Senior AI Systems Architect / Lead LLM Engineer

About the role

We are looking for a highly motivated Senior AI Systems Architect / Lead LLM Engineer to design and build the intelligence layer of a modern production software platform. This hands‑on senior position requires making high‑level architectural decisions and turning them into secure, scalable, production‑ready systems.

Key responsibilities

• Architect and implement scalable distributed systems for AI‑powered applications.
• Design end‑to‑end production LLM and agentic workflows.
• Build advanced Retrieval‑Augmented Generation (RAG) pipelines, including ingestion, chunking, embeddings, retrieval, reranking, evaluation, and citation.
• Develop reliable multi‑agent systems with orchestration, memory, tool use, permissions, and failure recovery.
• Create reusable Claude skills, tools, sub‑agents, and structured workflows.
• Integrate Model Context Protocols and connect AI agents with business systems.
• Define evaluation frameworks for accuracy, hallucination, latency, cost, and retrieval quality.
• Design secure AI infrastructure with observability, tracing, caching, rate limiting, and human‑approval controls.
• Make architectural decisions across APIs, databases, queues, event‑driven systems, vector stores, cloud infrastructure, and AI services.
• Establish engineering standards, mentor developers, and stay deeply involved in implementation.

Required profile

• Senior‑level software engineering and system architecture experience.
• Strong knowledge of distributed systems, micro‑services, event‑driven architecture, concurrency, scalability, and fault tolerance.
• Proven track record shipping LLM applications to production.
• Advanced hands‑on experience with RAG architecture and vector search.
• Current expertise with Claude, Claude Code, Claude skills, sub‑agents, and agentic development workflows.
• Experience designing multi‑agent systems and reliable AI orchestration.
• Strong backend engineering ability in Python, Go, or TypeScript.
• Experience with PostgreSQL, vector databases, Redis, message queues, APIs, containers, and cloud infrastructure.
• Deep understanding of AI security, prompt‑injection risks, data privacy, access controls, and production monitoring.
• Excellent communication skills and full ownership of delivery.

Required skills

• Python
• Go
• TypeScript
• PostgreSQL
• Vector databases (e.g., Pinecone, Milvus)
• Redis
• Message queues (e.g., RabbitMQ, Kafka)
• APIs (REST/GraphQL)
• Containers (Docker, Kubernetes)
• Cloud platforms (AWS, GCP, Azure)
• Claude, Claude Code, Claude skills, sub‑agents
• RAG pipelines, embeddings, hybrid retrieval, reranking
• Multi‑agent orchestration and tool calling
• Observability, tracing, caching, rate limiting
• Model fine‑tuning, LoRA, synthetic data pipelines