Agentic AI Engineer (human)

The role

The engineer will design and build the core agent harness, planning loops, and orchestration layers for a humanoid platform. This includes developing conversational AI pipelines, backend services, and evaluation systems to turn language models into reliable embodied agents.

What you will do

• Design and build the core agent harness for the humanoid platform
• Build systems that decompose high-level human intent into multi-step plans
• Orchestrate skills and sub-agents and track execution state
• Design the real-time voice stack including STT, LLM, and TTS pipelines
• Build the production backend including APIs and distributed services
• Deploy services across the edge-to-cloud NEURA ecosystem
• Stand up evaluation harnesses and observability to measure task completion
• Drive prototypes through to industrialized, deployed systems
• Work with hardware/software teams and external partners

Required qualifications

• Master's or PhD in Computer Science, Robotics, or a related field, or equivalent depth shown through shipped work
• Experience building production agent systems that plan, use tools, maintain state, and run reliably over long horizons
• Hands-on experience with agent frameworks and orchestration such as LangGraph, AgentCore, MCP, or custom orchestrators
• Professional backend engineering experience in production services, API and interface design, distributed and microservice architectures, clean code, testing, and DevOps discipline
• Cloud and edge-to-cloud experience including containerization (Docker, Kubernetes), CI/CD, and deploying and serving models and services in production
• Strong grounding in LLMs, VLMs, and NLP
• Excellent Python
• Excellent English

Nice to have

• German is a plus

About the company

NEURA Robotics develops cognitive robots that perceive, reason, plan over long horizons, and act autonomously in the physical world.