Location: Remote — Philippines
Type: Full-Time
Schedule: Mon–Fri, with at least 4 hours of CET overlap (2pm–11pm PHT)
Company Description
SwissPine Tech, founded in 2024 and headquartered in Geneva, connects Swiss startups and SMEs with top talent from the Philippines. Focusing on IT development, AI/ML solutions, blockchain technologies, and business process outsourcing, we deliver high-quality, cost-effective services under Swiss-level governance, data protection, and legal standards. Guided by our core values of honor, efficiency, positive attitude, leadership, and effective communication, we empower businesses while creating meaningful career opportunities.
Role Description
We are seeking a Senior AI Engineer to join an innovative AI product team building enterprise-grade LLM-powered applications and intelligent agentic workflows. Working directly with senior technical leadership, you will design, build, and optimize production-ready AI agents that power experimentation, research, and decision-support systems. This role is embedded with one of our AI product clients, working directly with the founders and senior technical leadership.
You will design, build, and optimize production-ready AI agents that power experimentation, research, and decision-support systems. This is a highly hands-on role for an engineer who enjoys solving complex backend challenges, writing production-quality code, and shaping technical architecture — someone who brings ideas and feedback to the table, not just implementation.
The ideal candidate combines deep .NET backend expertise with practical experience building production AI agents and integrating Large Language Models.
Key Responsibilities
- Design, develop, and optimize production-grade AI agent workflows using Anthropic, OpenAI, and modern agentic AI architectures.
- Develop and maintain backend services using .NET/C# while contributing to Python AI microservices using FastAPI or Django.
- Build scalable backend APIs supporting enterprise AI applications and agent orchestration.
- Integrate Anthropic, OpenAI, and other AI services into production applications.
- Design, test, and improve LLM-powered workflows through prompt engineering, grounding, evaluation, and iterative refinement.
- Collaborate closely with other Engineers, Data Scientists, and Product teams to improve AI performance and experimentation.
- Debug complex production systems independently and drive issues through to resolution.
- Participate in backend architecture discussions and recommend technical improvements.
- Build and maintain cloud-native applications deployed on Microsoft Azure and supported by GitHub Actions CI/CD pipelines.
- Stay current with emerging AI technologies and recommend improvements to agent architectures and enterprise AI capabilities.
Must-Have
- 6+ years of professional software engineering experience.
- Strong backend development experience using .NET/C# and React.
- Professional experience building production AI or LLM-powered applications.
- Strong Python development experience using FastAPI, Django, or similar frameworks.
- Hands-on experience building AI agents or agentic workflow solutions.
- Experience integrating Anthropic, OpenAI, or comparable Large Language Models into production applications.
- Experience designing and developing REST APIs and backend microservices.
- Excellent debugging and problem-solving skills with the ability to work independently.
- Previous experience as a Senior Software Engineer, Technical Lead, or Lead Engineer.
- Excellent debugging and problem-solving skills with the ability to work independently.
- Strong communication skills with the ability to contribute technical ideas and architectural discussions.
- Self-driven, proactive, and capable of working with minimal supervision.
- Reliable ability to work at least 4 hours of CET overlap daily.
Nice-to-Haves
- Experience building autonomous or multi-agent AI systems.
- Experience collaborating with Data Science or Machine Learning teams.
- Strong mathematical, statistical, or algorithmic foundation.
- Experience conducting AI research or experimentation.
- Experience evaluating LLM performance using grounding, benchmarking, or LLM-as-a-Judge methodologies.
- Experience deploying cloud-native applications on Microsoft Azure or AWS.
- Experience implementing CI/CD pipelines using GitHub Actions.
- Experience working on enterprise SaaS platforms.
- Experience mentoring engineers or leading technical initiatives.
- Strong ownership mentality with an experimental, solution-oriented mindset.
