About the company
This position is listed on behalf of a partner company, who manages all applications and next steps.
Responsibilities
- Architect, develop, deploy, and maintain production-grade LLM capabilities integrated into customer-facing products and internal workflows.
- Build backend services, APIs, integrations, and supporting infrastructure that connect AI capabilities with product functionality.
- Contribute to full-stack and user-facing development where required, helping deliver complete AI-powered product experiences.
- Implement production-ready patterns involving LLMs, RAG, embeddings, vector search, agents, and tool calling.
- Design reusable components, abstractions, and engineering patterns that improve development velocity, consistency, and maintainability.
- Establish and improve evaluation frameworks, observability, monitoring, and feedback loops for AI-powered features.
- Monitor and optimize AI systems for quality, latency, reliability, scalability, and inference cost.
- Investigate production issues, analyze telemetry, and continuously improve AI functionality based on system performance and user feedback.
- Collaborate closely with Product, ML, and Engineering stakeholders to translate product challenges into practical AI solutions.
- Rapidly prototype and validate new ideas, then transform successful experiments into robust and maintainable production systems.
- Contribute to engineering decisions around architecture, trade-offs, scalability, and long-term technical sustainability.
Requirements
- Demonstrated hands-on experience building and successfully shipping LLM-powered features or applications into production.
- Practical experience with technologies and patterns such as RAG, embeddings, vector search, agentic systems, LLM APIs, orchestration, and tool calling.
- Strong understanding of production LLM considerations, including evaluation, observability, failure modes, latency, reliability, and cost management.
- Experience improving AI features based on telemetry, evaluation results, production behavior, or user feedback.
- Strong software engineering background with experience designing APIs, backend services, and production-grade distributed systems.
- Full-stack development experience with technologies such as Angular, JavaScript/TypeScript, Python, Node.js, or comparable technologies is a strong advantage.
- Ability to write clean, maintainable, well-structured code and take ownership of solutions from implementation through production.
- Willingness and ability to contribute across backend services, AI infrastructure, and user-facing product functionality.
- Experience working with AWS or comparable cloud infrastructure, CI/CD pipelines, and production environments.
- Strong product mindset with a bias toward shipping, rapid iteration, pragmatic problem-solving, and measurable outcomes.
- Comfortable working in an environment characterized by ambiguity, rapid change, and evolving requirements.
- Strong communication and collaboration skills, with the ability to work effectively with Product, ML, and Engineering teams.
- Ability to challenge requirements constructively, communicate technical trade-offs, and translate AI complexity into practical product solutions.
- A maintainability- and reuse-oriented mindset, with a focus on building production systems rather than isolated demonstrations.
- Experience with multi-agent systems, MCP, guardrails, moderation, safety checks, prompt and context management, routing, caching, or fallback strategies is a plus.
- Experience with Docker and cloud platforms such as AWS, GCP, or Azure is beneficial.
- Experience with modern frontend development and customer-facing web applications is an advantage.
- This role is focused on applied AI engineering rather than heavy model training, academic research, custom ML algorithm development, or theoretical optimization work.
Conditions
- Highly visible role with direct access to senior leadership and meaningful influence on product and engineering decisions.
- Strong career growth and continuous learning opportunities in applied AI and software engineering.
- Opportunity to work alongside experienced technology, product, and industry professionals on high-impact AI initiatives.
- International and multicultural working environment with colleagues distributed across multiple countries.
- Flexible work-from-home arrangement.
- $500 home-office setup budget to support a productive remote working environment.
- $1,000 annual learning and development budget to support professional growth and skills development.
- Visa and relocation support where required.
- Opportunity to work on production-scale AI applications and modern LLM technologies.
- Significant ownership and autonomy in taking AI solutions from experimentation through deployment and continuous improvement.
- Competitive compensation aligned with experience, skills, and market standards.