Senior Developer - AI / ML

We are looking for a Senior Developer to help build the next generation of agentic AI frameworks that power Arctic Wolf's AI Proactive Defense platform. In this role, you will contribute to the development of intelligent agents capable of autonomous reasoning, decision-making, and proactive threat mitigation. You will work on multi-agent orchestration systems, LLM integration, and AI-driven automation pipelines that form the backbone of our AI-powered Security Operations Centre (SOC).

Responsibilities:

• Contribute to the design and development of agentic AI frameworks for proactive threat detection and response.
• Implement multi-agent coordination logic for planning, execution, and self-correction in dynamic security workflows.
• Integrate LLMs, vector databases, and tool-use APIs to enable contextual memory and autonomous reasoning.
• Build modular orchestration components for knowledge routing, task delegation, and agent collaboration.
• Collaborate with cross-functional teams to ensure production-grade scalability, observability, and resilience.
• Prototype and evaluate emerging agentic AI tools (e. g., LangChain, Semantic Kernel, LlamaIndex, AutoGen, CrewAI).
• Participate in code reviews, design discussions, and contribute to technical documentation.

Requirements:

• 5+ years of experience in backend software development, distributed systems, or applied AI engineering.
• Solid experience with Python, Go, or similar backend programming languages.
• Familiarity with LLMs and agentic AI frameworks such as LangChain, Semantic Kernel, or OpenAI/Anthropic APIs.
• Understanding of cloud-native architectures and microservices (AWS, GCP, or Azure).
• Passion for building intelligent systems that can reason, learn, and act autonomously.
• Strong problem-solving skills and a collaborative mindset.
• Experience working in agile, cross-functional teams.

Nice to Have:

• Exposure to cybersecurity, threat detection, or SOC operations.
• Experience with vector databases (e. g., FAISS, Pinecone) and retrieval-augmented generation (RAG).
• Familiarity with ML Ops tools and practices (e. g., MLflow, Kubeflow).
• Contributions to open-source AI or automation projects.