8 hours ago
Remote, Indonesia +4 moreSenior
Responsibilities
- Design and build backend services for AI-powered product features.
- Develop LLM inference pipelines and orchestration layers.
- Create reliable APIs for web, desktop, and mobile applications.
- Optimize latency, throughput, caching, batching, and streaming.
- Build monitoring, logging, alerting, and observability for production services.
- Debug distributed systems and improve platform reliability.
- Collaborate with product, infrastructure, and AI engineers to improve performance.
Requirements
- Strong production backend engineering experience.
- Experience building high-throughput, low-latency distributed systems.
- Excellent Python skills; Node.js experience is a plus.
- Hands-on experience deploying and operating services with Kubernetes and Docker.
- Experience with SQL and NoSQL databases.
- Familiarity with LLM inference, embeddings, or multimodal models.
- Pragmatic engineering mindset focused on shipping reliable software.
- Preferred: experience with OpenAI, Anthropic, open-source LLMs, AI orchestration, agent workflows, inference optimization, or operating AI services at scale.
Benefits
- Remote role on a founding AI engineering team.
- Cash and equity compensation are mentioned, but no amounts are specified.
- Opportunity to build AI infrastructure for a product intended for millions of users.
Categories
About OnHires
OnHires is a global recruitment and staffing agency that helps companies hire tech and creative talent, with focus areas including AI, Web3, blockchain, and DeFi. It provides IT recruiting and HR consulting services for startups and established firms, covering roles from engineers and designers to executives. Founded in 2020 and headquartered in Sheridan, Wyoming, OnHires is privately held.