Software Engineer (Agentic AI)

Job role

A dedicated startup is being formed to industrialize and scale a secure, AI-enabled, multi-source decision-support software offering. The platform is a multi-sensor fusion and agentic AI solution connecting to diverse data sources (for example geospatial layers, imagery, video, and other operational signals). This role will support the delivery of a scalable product and contribute to establishing the processes, standards, and collaboration practices required for sustainable growth.

The Agentic AI Engineer is responsible for designing, developing, and deploying intelligent autonomous systems that can reason, plan, and act with minimal human intervention. This role focuses on building agent-based architectures, orchestrating multi-agent workflows, and integrating advanced AI models with tools, APIs, and real-world environments. The ideal candidate combines deep technical expertise in AI engineering with strong software architecture skills, enabling the creation of scalable, reliable, and secure agentic solutions.

Job Responsibilities

• Design and implement agentic AI systems capable of autonomous decision-making, tool use, and multi-step task execution.
• Architect and build multi-agent frameworks, including planning, coordination, memory, and feedback loops.
• Integrate LLMs and other AI models with external tools, APIs, databases, and enterprise systems.
• Develop robust agent orchestration layers, including task routing, context management, and safety controls.
• Implement scalable backend services to support agent execution, state management, and event-driven workflows.
• Optimize agent performance through prompt engineering, model fine-tuning, retrieval-augmented generation (RAG), and caching strategies.
• Collaborate with product, data, and engineering teams to design end-to-end agentic solutions for real business use cases.
• Ensure agent systems adhere to security, privacy, and compliance requirements.
• Build monitoring, logging, and evaluation pipelines to track agent behavior, reliability, and performance.
• Conduct root-cause analysis and debugging for complex agent behaviors and emergent system issues.
• Maintain documentation for agent architectures, design patterns, and operational procedures.

Qualifications & Experience

• Typically 5+ years of relevant experience in a fast-paced product environment.
• Bachelor's or Master's degree in Computer Science, Engineering, AI/ML, or equivalent practical experience.
• 3-5 years of experience in AI engineering, machine learning, backend engineering, or related fields.
• Strong hands-on experience with LLMs, AI frameworks, and agentic toolchains (LangChain, LlamaIndex, OpenAI tools, custom agent frameworks, etc.).
• Proficiency in Python (required) and familiarity with additional languages such as TypeScript, or C++ is a plus.
• Solid understanding of software architecture, distributed systems, and event-driven design.
• Experience building systems that integrate with APIs, databases, vector stores, and messaging brokers.
• Familiarity with RAG pipelines, embeddings, vector databases, and model fine-tuning.
• Experience with cloud platforms, like AWS, and container orchestration (Docker, Kubernetes).
• Knowledge of CI/CD pipelines, GitHub workflows, and modern DevOps practices.
• Understanding of AI safety, evaluation, and guardrail frameworks is a plus.

Competencies

• Strong analytical and problem-solving skills, especially in complex or ambiguous AI-driven systems.
• Ability to design scalable, modular, and resilient agentic architectures.
• Excellent communication and cross-functional collaboration abilities.
• High attention to detail and commitment to reliability and safety in AI systems.
• Proactive mindset with a passion for innovation, automation, and continuous improvement.
• Ability to work independently, manage multiple priorities, and drive projects fro