Job Description
We are at the precipice of a technological revolution. As we look toward the year 2026 and beyond, Nexus Horizon Systems is seeking a visionary Agentic AI Architect to lead the charge in building autonomous, self-improving systems. You won't just be writing code; you will be architecting the cognitive infrastructure of the future.
In this role, you will design and deploy sophisticated AI agents capable of complex reasoning, planning, and execution. You will bridge the gap between theoretical AI research and production-grade software engineering, ensuring our solutions are scalable, ethical, and transformative.
Responsibilities
- Design and implement multi-agent architectures that leverage Large Language Models (LLMs) for autonomous decision-making.
- Develop robust prompt engineering frameworks and retrieval-augmented generation (RAG) pipelines.
- Optimize model inference for low-latency, high-throughput environments using edge computing and distributed systems.
- Establish best practices for AI safety, alignment, and bias mitigation in agent workflows.
- Collaborate with cross-functional teams to integrate AI agents into core product ecosystems.
- Stay ahead of the curve on emerging AI paradigms, including ReAct (Reasoning + Acting) patterns and tool use.
Qualifications
- Ph.D. or Master's degree in Computer Science, Artificial Intelligence, or a related technical field.
- 7+ years of experience in software engineering, with a strong focus on AI/ML.
- Deep expertise in Python, Rust, and modern ML frameworks (PyTorch, TensorFlow, LangChain).
- Proven track record of deploying production-level LLM applications.
- Experience with vector databases (Pinecone, Milvus, Weaviate) and semantic search.
- Strong understanding of system design principles, cloud infrastructure (AWS/GCP), and containerization (Docker/K8s).