Agentic AI Engineer

Flat Rock Technology is a technology-driven organisation focused on building robust, scalable software solutions for a global client base. We value clean architecture, pragmatic problem-solving, and continuous improvement, and we foster an environment where experienced engineers can have real technical influence.

We are looking for an Agentic AI Engineer to design, build, and deploy AI agents capable of autonomous reasoning, decision-making, and self-directed task execution. In this role, you will architect intelligent systems that go beyond simple prompt-response interactions - creating agents that can plan multi-step tasks, use tools, interact with enterprise systems, and complete complex workflows end-to-end with appropriate guardrails and human oversight.

You will work across the full lifecycle - from research and prototyping through to production deployment and monitoring. Collaborating closely with product managers, data scientists, software engineers, and business stakeholders, you will translate real operational challenges into production-grade agentic solutions that drive measurable business impact.

**

Main responsibilities:**

• Design and build agentic AI systems, including autonomous agents, multi-agent orchestration, workflow state machines, and tool-using agents.
• Develop LLM-driven agents capable of reasoning, planning, retrieval (RAG), and task execution across enterprise systems.
• Build and maintain AI-powered automation workflows using platforms like n8n and Make to orchestrate business processes and cross-application integrations.
• Integrate agents with APIs, CRM/ERP systems, collaboration tools, databases, and payment platforms using tool/function calling, MCP, and A2A patterns.
• Implement robust execution logic (validation, retries, rate limits, fallbacks, error handling) to ensure reliability and scalability.
• Design and manage RAG pipelines using embeddings, vector databases, chunking, and reranking strategies.
• Establish safety guardrails, access controls, and human-in-the-loop workflows for high-risk actions.
• Build evaluation, observability, and tracing pipelines to monitor performance, cost, latency, and reliability.
• Deploy and operate agent services in cloud environments (AWS, Azure, or GCP) using Docker, Kubernetes, Terraform, and CI/CD.
• Monitor production systems, troubleshoot issues, and continuously improve agent performance and policies.
• Prototype and benchmark emerging agentic AI frameworks and models.
• Create technical documentation and communicate AI solutions effectively to cross-functional stakeholders.

**

Requirements:**

• Bachelor’s or Master’s degree in Computer Science, AI, Engineering, or related field.
• 3+ years of software engineering experience (Python and/or TypeScript).
• 1+ year building LLM-powered or agentic AI systems in production or near-production environments.
• Experience with agent frameworks (e.g., LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel).
• Hands-on experience with automation/orchestration tools (e.g., n8n, Make) in production settings.
• Strong understanding of LLMs, embeddings, prompt engineering, structured outputs, and tool calling.
• Experience designing REST APIs, microservices, and backend systems.
• Familiarity with vector databases and RAG architectures.
• Strong system design, debugging, and communication skills.

**

Preferable skills:**

• Experience with MCP, A2A, or advanced agent communication patterns.
• Advanced experience with n8n (custom nodes, self-hosting) or Make (complex scenarios).
• Experience combining LLMs with workflow engines for document processing, reporting, chatbots, or decision support.
• Familiarity with AI evaluation and observability tools (e.g., LangSmith, OpenAI Evals, Weights & Biases).
• Experience with multi-agent systems, planning algorithms, RL, fine-tuning, or RLHF.
• Experience with cloud platforms (AWS, Azure, or GCP), containerization (Docker, Kubernetes), and infrastructure-as-code tools.
• Knowledge of CI/CD pipelines and security best practices.
• Experience in regulated industries (e.g., healthcare, finance, defense).
• Relevant cloud or ML certifications.

**

We offer:**

• Competitive salaries based on performance reviews with additional benefits;
• Opportunities for professional growth and career development;
• Supportive environment with mentoring from senior engineers;
• Challenging work in a fast-growing international organization;
• Opportunity to work on real-world, production systems;
• Hybrid working arrangements;
• Modern offices around the world;
• Entertainment spaces, teambuilding events, parties, and participation in different events;

If that sounds just like you, apply now by sending your CV in English!

By submitting your application you agree that FRT will use your personal data for recruitment purposes only. All documents will be treated in the strictest confidentiality.

Only short-listed candidates will be invited for an interview.

We can not wait to meet you!