Senior Agentic AI Software Engineer

About the Position

We are looking for a Senior Agentic AI Software Engineer to build production-ready agentic capabilities for a B2B intelligence platform, working directly with the CPTO to extend Hermes Agent with new features, skills, tools, and integrations. You will design single-agent and multi-agent workflows, build evaluation frameworks for agent behavior and model performance, modernize existing B2B workflows into reliable agent-driven processes, and integrate model APIs across Microsoft Foundry, AWS Bedrock, and compatible providers. This is a 6-month engagement based in LatAm requiring regular overlap with US West Coast hours.

Responsibilities

• Build features, skills, tools, integrations, and workflows on top of Hermes Agent.
• Modernize selected existing B2B workflows, including information sourcing and newsletter generation, into controlled, end-to-end agent-driven processes.
• Design provider-independent model integrations across Microsoft Foundry (formerly Azure AI Foundry), AWS Bedrock, and compatible model APIs.
• Contribute to model-governance capabilities, including approved models and providers, policy enforcement, permissions, and deployment controls.
• Use GitHub Enterprise and AI-assisted development tools to implement, test, and iterate on agent-driven product capabilities.
• Work closely with InfoDesk leadership to deliver releasable product increments approximately every four weeks.
• Define and run evaluations for agent behavior and model performance, including success criteria, rubrics, regression tests, benchmarks, and failure analysis.
• Design single-agent and multi-agent workflows based on the needs of each use case.
• Integrate agent capabilities into user-facing interfaces, such as Hermes Desktop or CLI tools, as needed.

Requirements

• Hands-on experience building agentic applications or workflows with Hermes Agent, OpenClaw, or another relevant agent framework, with the ability to ramp up quickly on Hermes.
• Senior-level software engineering experience (4+ years) building and shipping production applications or platforms.
• Strong experience with backend or full-stack development, including APIs, integrations, asynchronous workflows, testing, debugging, and system design.
• Experience designing and operating evaluations for LLM or agent-based systems, including identifying failure modes and measuring improvements.
• Experience integrating LLMs through model APIs or cloud model platforms and designing systems that are not tightly coupled to a single provider.
• Demonstrable experience building agent skills, plugins, automations, integrations, or applications. This may come from professional work, internal projects, personal projects, or open-source contributions.
• Strong end-to-end systems thinking and the ability to work effectively with existing products, legacy codebases, and complex edge cases.
• Ability to understand ambiguous business requirements and translate them into practical technical solutions.
• Ability to discuss and demonstrate recent hands-on experiments with agent workflows, including the decisions made, limitations encountered, and results achieved.
• Strong verbal communication and the ability to work directly with executive and product leadership.
• Availability for regular overlap into the US West Coast afternoon.
• Upper-intermediate English level.

Nice to Have

• Direct development experience with Hermes Agent or contributions to its ecosystem.
• Experience with GitHub Enterprise-based AI-assisted development workflows, including graph-based orchestration and configuration of agent instructions, tools, skills, or workspace rules.
• Experience building model-governance, policy-enforcement, or provider-selection capabilities.
• Experience with portable, cloud-native deployment using containers, Kubernetes, or related CNCF ecosystem technologies.
• Experience with Electron applications, CLI tools, or Microsoft Teams and other enterprise messaging integrations.
• Experience running local or open-weight models, including smaller task-specific models.
• Awareness of harness-aware model adaptation or post-training techniques.

We Offer

• Growth without limits: build your skills through mentorship, internal TechTalks, challenging projects, and a dedicated annual learning budget.
• Competitive compensation: get recognition that reflects your skills and impact, with regular performance and compensation reviews.
• Flexibility: work 100% remotely with flexible hours that support focus, autonomy, and a healthy work rhythm.
• Meaningful, modern projects: build impactful products using modern technologies alongside global teams and leading brands.
• Collaborative culture: join a supportive environment with zero micromanagement where ideas are welcomed and contributions are recognized.
• Well-being & support: access local well-being programs and people-focused support tailored to your location.

About the Company

At AgileEngine, we are committed to building innovative solutions that drive business success. Our team of experts works on cutting-edge projects, leveraging the latest technologies to deliver exceptional results. We value creativity, collaboration, and continuous learning, fostering an environment where you can grow and make a significant impact.