Forward Deployed Agile Software Engineer

About the Role

This opportunity involves working with a partner company based in Saudi Arabia, focusing on integrating advanced software development, artificial intelligence (AI), and product innovation to solve complex business issues. As a Forward Deployed Agile Software Engineer, you will engage closely with clients, translating unclear needs into functional, production-ready AI-driven software solutions. Your responsibilities span designing AI-powered applications, autonomous agents, intelligent workflows, and full-stack systems tailored to actual business demands. You will contribute beyond building models by engineering the surrounding infrastructure that ensures AI applications are dependable, secure, observable, and scalable.

Key Responsibilities

• Collaborate directly with clients and internal teams to uncover business goals, workflow operations, technical landscapes, data environments, and limitations; transform vague challenges into actionable plans involving design, prototyping, and solutions deployment.
• Develop and release AI-based applications, agentic workflows, APIs, developer tools, data pipelines, and comprehensive products addressing practical business purposes.
• Engineer the supporting systems for AI models, including prompt delivery, context handling, memory management, permissions, runtime monitoring, and feedback systems to guarantee reliable operation in production.
• Design and optimize agent orchestration involving planning, tool selection, execution, evaluation, and fallback mechanisms using graphs, state machines, and orchestration patterns integrating models, systems, data, and human approval flows.
• Create and maintain evaluation frameworks and testing procedures to assess task success, accuracy, safety, latency, cost efficiency, and user satisfaction, leveraging datasets, regression tests, human reviews, and feedback loops.
• Produce prototypes rapidly, validate them through real user testing, and transition effective prototypes into secure, scalable, and maintainable production software.
• Integrate AI solutions seamlessly with client enterprise systems, data sources, cloud platforms, APIs, databases, and third-party tools, respecting existing technological environments.
• Implement safety, security precautions, approval workflows, and fallback strategies to prevent AI-related risks such as hallucinations, prompt injection, context loss, erratic loops, unreliable tool calls, and unsafe executions.
• Apply observability best practices to log traces, intermediate steps, performance indicators, and failures, diagnosing and resolving intricate technical and operational challenges.
• Uphold software engineering excellence through automation, documentation, security, version control, observability, and continuous integration and delivery practices.
• Communicate effectively across multidisciplinary teams—including product managers, designers, engineers, data analysts, security professionals, and stakeholders—explaining technical decisions, constraints, trade-offs, and progress clearly.
• Promote knowledge exchange by developing reusable components, technical templates, and best practices; contribute to discovery, showcasing solutions, workshops, and sales support when necessary.

Candidate Requirements

• Proven experience in software engineering with a history of delivering production-grade software, particularly AI-driven applications or autonomous systems.
• Strong programming skills in Python, TypeScript, or other relevant languages used for AI products, platforms, and tooling.
• Solid understanding of harness engineering encompassing infrastructure, context management, tools, permissions, runtime control, and feedback loops ensuring reliable AI agent performance.
• Familiarity with designing agentic workflows involving planning, executing, observing, reflecting, and recovery phases.
• Knowledge of workflow orchestration using graph-based structures, state machines, and complex multitier processes that integrate agents, tools, data, and human input.
• Experience in building evaluation and testing systems for AI applications, including benchmarks, regression testing, human-in-the-loop review, and production monitoring.
• A comprehensive understanding of AI model considerations such as prompt design, memory, retrieval methods, tool usage, structured outputs, model selection, quality, latency, and cost trade-offs.
• Expertise in observability and debugging for AI systems to monitor decision-making, inspect intermediate states, analyze quality, and troubleshoot errors.
• Strong foundations in APIs, distributed computing, databases, cloud infrastructure, and modern development methodologies.
• Excellent problem-solving skills, adaptability in learning new technologies and domains, and ability to clarify ambiguous client needs into practical and tested software solutions.
• Sound product judgment balancing capability, reliability, security, latency, cost-effectiveness, maintainability, and user experience.
• Experience interacting directly with clients or cross-functional teams to build trust and manage evolving project demands.
• Exceptional communication abilities to convey AI functionalities, risks, limitations, and technical trade-offs to diverse audiences.
• A proactive, curious, accountable, and empathetic mindset, thriving in agile, fast-changing environments.
• Readiness to travel occasionally for client workshops or onsite engagements.

Preferred Qualifications

• Hands-on experience with agent frameworks, workflow engines, coding agents, or model orchestration platforms.
• Development of tool interfaces, execution sandboxes, permission models, and human-in-the-loop controls for autonomous or semi-autonomous AI systems.
• Familiarity with RAG (retrieval-augmented generation), embeddings, vector search, knowledge graphs, fine-tuning, and model routing methodologies.
• Proficiency with AI evaluation techniques such as golden datasets, adversarial testing, simulations, live experiments, and feedback-based improvements.
• Knowledge of AI observability tools involving execution tracing, token/cost analysis, latency monitoring, error classification, and quality dashboarding.
• Experience creating multi-model AI systems or specialized agents collaborating on complex tasks.
• Understanding of AI security challenges like prompt injection, data exposure, unreliable tool usage, excessive autonomy, and supply chain vulnerabilities.
• Experience with cloud platforms (AWS, Azure, Google Cloud), containerization, Kubernetes orchestration, infrastructure as code, and CI/CD pipelines.
• Contributions to open-source AI infrastructure, agent frameworks, or evaluation tooling.
• Direct experience in regulated or complex enterprise settings.
• Background in consulting, professional services, solutions or sales engineering, or other client-facing technical roles.
• Track record of taking products from ideation through to production and adoption phases.
• Claude Certified Architect credentials or equivalent qualifications with practical experience in Claude-based AI deployments.
• Documented expertise in agentic AI and harness engineering, focusing on reliable, scalable autonomous systems and workflows.

Application Notes

Candidates lacking some listed skills but possessing related experience and strong interest are encouraged to apply.

Benefits

• Engage with meaningful, high-impact software development challenges across various sectors and technologies.
• Experience hands-on product development with opportunities to deploy real-world AI and software solutions.
• Collaborate directly with clients for greater impact and visibility of your work.
• Gain exposure to cutting-edge AI technologies, agentic engineering, and modern delivery approaches.
• Work within cross-functional teams fostering experimentation, knowledge sharing, and continuous skill advancement.
• Influence engineering approaches and contribute reusable technical assets across projects.
• Enjoy ownership and autonomy managing complex problems from concept to production.
• Become part of an inclusive culture embracing diversity, transparency, equal opportunity, and thoughtful innovation.
• Remote work flexibility with occasional travel for client engagements as needed.