Senior Agentic AI Engineer
- Pay
- Not stated
- Required
- Python, Amazon Bedrock, AWS, Retrieval-augmented generation
- Nice to have
- Model Context Protocol, multi-agent frameworks, Containerization, Infrastructure as Code
- Experience
- 5+ years
- Benefits
- Flexible hours, Health insurance, Sports club membership, My Benefit – cafeteria system access
- Posted
- October 30, 2026
- Company
- Verita HR
Who it can hire
We read the post for each of the 21 countries we cover.
Open to people in Poland
The employer lists this job as remote there: “Poland”.
Not open to people in the other 20 countries we cover, as far as the post says.
The job post
- Remote working
- Comprehensive premium health insurance
- Sports club membership
- My Benefit – cafeteria system access
- Competitive compensation package
- Support for tuition and continued education
- Active sports and social events committee
We are looking for an experienced Senior Agentic AI & Harness Engineer to join a technology-driven organization developing advanced AI solutions for complex enterprise environments.
The role focuses on building scalable, secure, and production-ready AI agent systems that automate business processes, integrate with enterprise applications, and support operational decision-making.
You will play a key role in designing the infrastructure and engineering frameworks that enable AI agents to operate reliably in real-world environments. Working closely with software engineering, data, cloud, and security teams, you will help establish technical standards and reusable solutions for enterprise AI adoption.
- At least 5 years of professional software engineering experience, including hands-on experience delivering LLM-powered or agent-based solutions in production.
- Advanced Python programming skills and strong knowledge of modern software engineering practices.
- Practical experience developing AI agents, orchestration frameworks, and LLM-based applications.
- Solid understanding of retrieval-augmented generation (RAG), context engineering, memory management, and tool-calling mechanisms.
- Experience implementing asynchronous processing, API integrations, stateful workflows, and fault-tolerant systems.
- Strong knowledge of AWS cloud services and experience working with managed LLM platforms such as Amazon Bedrock or similar technologies.
- Experience designing automated tests, evaluation pipelines, and regression testing for AI-powered applications.
- Understanding of application security, authorization mechanisms, and secure integration patterns.
- Familiarity with CI/CD pipelines, version control, and production deployment practices.
- Strong problem-solving skills and the ability to troubleshoot complex distributed systems.
- Good communication skills and experience collaborating with multidisciplinary engineering teams.
Nice to have:
- Experience working in financial technology, enterprise software, or regulated industries.
- Knowledge of Model Context Protocol (MCP), model gateways, and advanced tool integration architectures.
- Experience with multi-agent frameworks and workflow orchestration technologies.
- Familiarity with containerization, infrastructure as code, and cloud-native architectures.
- Knowledge of AI governance, responsible AI practices, and model risk management.
- Experience building internal AI platforms, shared engineering libraries, or reusable development frameworks.
- Relevant cloud, AI, or security certifications.
- Experience providing technical guidance or mentoring other engineers.
- Design, develop, and maintain production-grade AI agent architectures and execution frameworks.
- Build agent orchestration mechanisms covering task planning, context management, retrieval, memory, and tool interaction.
- Develop reliable workflows incorporating state persistence, checkpointing, retry strategies, error recovery, and execution safeguards.
- Integrate LLM-based solutions with internal applications, APIs, databases, and enterprise services.
- Implement security and governance mechanisms, including access controls, approval workflows, input validation, and protection against prompt injection.
- Ensure appropriate separation between AI-driven decision-making and deterministic business logic.
- Create automated testing and evaluation frameworks to assess agent accuracy, reliability, tool usage, and overall performance.
- Establish monitoring and observability capabilities to track system behavior, execution quality, latency, and operational costs.
- Identify opportunities to improve agent performance, scalability, and maintainability.
- Collaborate with cross-functional teams to deliver AI solutions from initial design through production deployment.
- Contribute to architectural decisions, technical documentation, and engineering best practices.
First Monday isn’t the employer or a recruiter and isn’t affiliated with Verita HR. Details may have changed since; confirm with the employer before you apply.