Role summary
You will join the core backend team responsible for the entire Generative AI task delivery stack. This is production infrastructure that needs to scale over the next months. Your work directly impacts latency, cost per generate, and system reliability for every customer, also you'll be responsible for feature development collaborating with product team and cross‑functional partners (ML, frontend, design). This is a full‑time, role for engineers with 3+ years of backend experience.
Key responsibilities
- Design and maintain high-throughput microservices
- Design and implement feature epics in collaboration with product managers
- Find solutions to optimize and enhance AI infrastructure
- Collaborate with ML engineers to productionize research models quickly and safely
- Own service reliability through robust observability, monitoring, and alerting.
- Contribute to code reviews, technical documentation, and secure coding practices.
- Build and improve CI/CD pipelines for safe, frequent deployments.
Required qualifications
- Backend engineering experience with Golang
- Strong knowledge in concurrency
- Familiarity with docker and monitoring systems
- 3+ years of experience building production backend services at scale (or equivalent).
- Experience with relational and NoSQL databases.
- BSc in Computer Science, Engineering, or related field, or equivalent practical experience.
Preferred qualifications
- Hands-on experience with design and implementation of AI pipelines
- Familiarity with Generative AI models
- Experience tuning low-latency, cost‑efficient inference services and GPU/accelerator workloads.
Compensation and benefits
- Competitive salary
- Comprehensive health care coverage
- Access to our in‑house AI design and development tools for day‑to‑day work