Senior AI Engineer (Agentic Systems)

Job Title: Senior AI Engineer (Agentic Systems / On-Premise AI)

Location: On-site (In-Person Only)

About the Role

We are seeking a highly experienced Senior AI Engineer to join our team and help build the next generation of sovereign AI systems. Unlike conventional approaches that rely on closed-source APIs, this role focuses on designing, deploying, and scaling fully private, on-premise AI infrastructure.

This position is ideal for engineers who go beyond prompt engineering, from model inference to multi-agent orchestration. You will play a critical role in building intelligent systems that reason, execute, and operate across complex, stateful workflows while prioritizing data security and hardware efficiency.

Key Responsibilities

• Architect and implement multi-agent systems using frameworks such as LangGraph or PydanticAI
• Design advanced agentic workflows including planning, self-reflection, and multi-agent coordination
• Build and optimize production-grade Retrieval-Augmented Generation (RAG) pipelines with hybrid search and re-ranking
• Manage and optimize on-premise inference infrastructure, balancing latency and throughput on GPU clusters
• Design resilient, stateful systems capable of long-running processes, error handling, and human-in-the-loop interactions
• Develop automated evaluation and benchmarking frameworks to measure agent performance and reliability
• Own the end-to-end lifecycle of AI systems, from development through deployment and optimization

Technical Requirements

AI & Backend (Python / Systems Engineering)

• Expert-level proficiency in Python, including asynchronous programming
• Strong experience building production-grade backend systems (FastAPI, Pydantic)
• Deep understanding of agentic frameworks such as LangGraph or PydanticAI
• Advanced knowledge of RAG systems, vector search, and ranking strategies
• Strong grasp of large language model fundamentals (attention mechanisms, KV caching, tokenization impact)

Infrastructure & Deployment

• Proven experience deploying open-weight models (e.g., Llama, Mistral, DeepSeek)
• Hands-on experience with local inference engines (vLLM, TGI, TensorRT-LLM)
• Experience managing GPU-based workloads on bare-metal or private Kubernetes environments
• Ability to optimize performance across hardware constraints (latency, throughput, memory usage)

Additional Qualifications

• Experience designing complex, stateful AI systems and workflows
• Strong problem-solving skills with a systems-level mindset
• Ability to work independently in a high-performance engineering environment
• Excellent communication and collaboration skills

Preferred Qualifications

• Experience with model training and refinement, including pretraining and post-training techniques (SFT, DPO, ORPO, RLHF)
• Knowledge of model optimization techniques such as quantization, distillation, and graph optimization
• Experience managing GPU memory and optimizing VRAM usage across different model sizes and workloads
• Familiarity with data curation, dataset preparation, and domain-specific model tuning
• Strong interest in data sovereignty, privacy, and infrastructure ownership

Requirements

• Must be able to work fully on-site
• Must have experience with:
• Python and backend system development
• AI / Generative AI systems
• Agentic workflows and LLM-based architectures
• Infrastructure-level optimization and deployment

Work Environment

This is a fully in-person role. Remote or hybrid work is not available for this position.

Why Join Us

• This is an opportunity to work at the forefront of sovereign AI, building systems that prioritize control, performance, and privacy. You will have the chance to work with cutting-edge technologies and solve complex challenges that go far beyond traditional AI applications.