Senior Backend Engineer, AI Systems
Company: Asahan Tech Partners
Location: Remote
Employment Type: Full-time
Experience Level: Senior — 5+ years
About the Role
Asahan Tech Partners is seeking a Senior Backend Engineer, AI Systems to design, build, and maintain scalable backend services that support AI-powered applications.
You will work on production backend systems, API development, cloud infrastructure, database architecture, and integrations with large language models and other AI services. The ideal candidate has strong backend engineering experience and understands how to move AI features from prototypes into reliable production systems.
Responsibilities
- Design, develop, and maintain scalable backend services and APIs.
- Build backend systems that integrate with large language models and third-party AI services.
- Develop retrieval-augmented generation pipelines, AI workflows, and data-processing services.
- Design secure and reliable microservice architectures.
- Improve application performance, scalability, availability, and observability.
- Work with relational and NoSQL databases.
- Deploy and maintain backend services in cloud environments.
- Implement authentication, authorisation, logging, testing, and error-handling systems.
- Review code and contribute to technical architecture decisions.
- Troubleshoot production issues and improve system reliability.
- Collaborate with product, frontend, AI, and infrastructure teams.
Required Qualifications
- At least five years of professional backend engineering experience.
- Strong experience with Python and backend frameworks such as FastAPI, Django, or Flask.
- Experience designing and building REST APIs and microservices.
- Experience with PostgreSQL or another relational database.
- Experience with cloud platforms such as AWS, Google Cloud, or Microsoft Azure.
- Experience with Docker and modern deployment workflows.
- Understanding of automated testing, CI/CD, monitoring, and production support.
- Experience integrating external APIs and third-party services.
- Strong understanding of system design, security, scalability, and software engineering best practices.
- Ability to work independently in a remote environment.
AI Experience
Candidates should have practical experience with at least some of the following:
- Large language model API integration.
- Retrieval-augmented generation systems.
- Vector databases and semantic search.
- Prompt and response management.
- AI workflow or agent orchestration.
- Document processing and embedding pipelines.
- Model output evaluation, monitoring, and error handling.
- Production deployment of AI-powered features.
Preferred Qualifications
- Experience with OpenAI, Anthropic, Google Gemini, or open-source language models.
- Experience with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, or pgvector.
- Experience with message queues or event-driven systems.
- Experience with Kubernetes, Terraform, or infrastructure as code.
- Experience building SaaS products or multi-tenant platforms.
- Experience leading technical projects or mentoring developers.
- Familiarity with AI security, privacy, cost optimisation, and model observability.
What We Offer
- Fully remote work worldwide
- Opportunity to build production AI systems.
- Meaningful ownership of backend architecture and technical decisions.
- Flexible and collaborative working environment.
- Competitive compensation based on experience.
- Opportunities for professional growth and technical leadership.
How to Apply
Please submit:
Qualified candidates will be contacted for an introductory interview followed by a technical interview.
