# Agentic AI Engineer at Flatrock

> Sri Lanka · Unspecified · ML / AI · open. Source: https://alderhq.app/jobs/personio%3Aflatrock%3A2534354 (read 2026-11-09).

## Facts (observed)

- Company: [Flatrock](https://alderhq.app/companies/flatrock)
- Location text: Colombo
- Where it can be done from (inferred): Sri Lanka (evidence: "Location: Colombo")
- Posted: 2026-02-18 (264 days ago)
- First seen by alder: 2026-11-04 · last verified: 2026-11-08
- Reposted: 0 times · edited: 0 times
- Apply on the employer's site: https://flatrock.jobs.personio.de/job/2534354
- Skills listed (inferred): TypeScript, Node.js, Python, AWS, GCP, Azure, Kubernetes, Docker, Terraform, LLMs, Distributed systems

## Pay and sponsorship

- Posted pay: not posted

## Description (the employer's text)

### Main responsibilities

- Design and develop agentic AI systems including autonomous agents, tool-using agents, multi-agent orchestration, and workflow state machines
- Design, build, and maintain AI-powered automation workflows
- Build LLM-driven agents capable of reasoning, planning, retrieving knowledge, and executing tasks across enterprise systems
- Integrate agents with internal APIs, CRM/ERP platforms, Jira, Confluence, Slack, email, databases, payment systems, and other business tools using function/tool calling, MCP (Model Context Protocol), and A2A patterns
- Develop end-to-end AI automations that combine LLM capabilities solving repetitive tasks such as document processing, lead enrichment, customer support triage, reporting, and data synchronisation across systems
- Connect AI agents to automation platforms via webhooks, API triggers, and custom nodes; manage scheduling, error handling, and conditional branching within automation workflows
- Implement tool-calling schemas, input validation, error handling, retries, rate limits, and fallback logic to ensure reliable agent execution
- Design and maintain RAG pipelines using vector databases, embedding models, reranking, and chunking strategies to ground agent outputs in enterprise knowledge
- Build safety guardrails including content filters, policy constraints, tool access controls, and human-in-the-loop approval flows for high-risk actions
- Create evaluation pipelines to measure agent reliability, task success rate, accuracy, and failure-mode behaviour using tools such as LangSmith, OpenAI Evals, or custom telemetry systems
- Implement observability and tracing of reasoning steps, tool calls, latency, cost, and error rates to support debugging and continuous improvement
- Deploy and operate agent services using Docker, Kubernetes, Terraform, and CI/CD pipelines in cloud environments (AWS, Azure, or GCP)
- Monitor agent behaviour in production, diagnose anomalies, and continuously refine agent policies and performance
- Evaluate emerging agentic AI models, frameworks, and toolkits; prototype and benchmark new approaches for scalability, robustness, and safety
- Prepare technical documentation including architecture diagrams, capability descriptions, limitations, and operational guidelines
- Communicate complex AI concepts to non-technical stakeholders and collaborate across cross-functional teams to align solutions with business needs
### Requirements

- Bachelor's or master's degree in computer science, AI, Data Science, Engineering, or a related field
- 3+ years of software engineering experience with strong proficiency in Python and/or TypeScript
- 1+ year of hands-on experience building LLM-powered applications or agentic AI systems in production or near-production settings
- Experience with agent frameworks such as LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or equivalents
- Hands-on experience with AI automation and workflow orchestration
- Solid understanding of LLMs, embeddings, prompt engineering, structured outputs, and function/tool calling
- Experience building and integrating REST APIs, microservices, and backend services
- Familiarity with vector databases (FAISS, Pinecone, Chroma, Weaviate) and RAG pipeline design
- Familiarity with AI-assisted development workflows (e.g., Cursor, GitHub Copilot, Claude Code) for research, architecture, and implementation
- Strong system design, debugging, and problem-solving skills
- Excellent communication skills with the ability to present technical concepts to non-technical audiences
- Experience with agent communication protocols such as MCP (Model Context Protocol) and A2A
- Experience designing AI automation solutions that combine LLMs with workflow engines for use cases such as intelligent document processing, automated reporting, chatbot backends, or AI-assisted decision support
- Experience with cloud platforms (AWS, Azure, or GCP) and cloud AI services such as Azure AI Foundry, AWS Bedrock, or Google Vertex AI
Preferred:

- Advanced experience with n8n (including custom node development and self-hosting) or Make (including advanced scenario design, iterators, and aggregators)
- Experience with evaluation and observability tools for AI agents (LangSmith, OpenAI Evals, Weights & Biases, or custom telemetry)
- Experience with reinforcement learning, planning algorithms, or multi-agent coordination
- Familiarity with model fine-tuning, RLHF, or distillation techniques
- Experience with CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins)
- Experience with containerisation (Docker, Kubernetes) and infrastructure-as-code tools (Terraform, CloudFormation)
- Knowledge of security best practices: authentication, authorisation, least-privilege access, and audit logging
- Background in a regulated industry (healthcare, finance, defence, or consulting)
- Relevant certifications: AWS ML Specialty, Azure AI Engineer Associate, or GCP Professional ML Engineer

---
Data: alder (https://alderhq.app). Cite https://alderhq.app/jobs/personio%3Aflatrock%3A2534354 and the date you read it. Observed facts come from the employer's own listing; location reach, level, family and skills are inferences.