Responsibilities
- Collaborate with the inference engineering team to enhance system performance in terms of response time and processing capacity
- Implement support for cutting-edge AI models and advanced inference techniques, including quantization methods
- Improve efficiency of inference operations across all layers, from low-level GPU computations to API serving infrastructure
Compensation
Final offer amounts are determined by multiple factors, including experience and expertise, and may vary
Work Arrangement
Hybrid — London
Other
- Internship duration: 13 weeks
- Work schedule: full-time or part-time
- Hybrid schedule: 3 days from the office, 2 days WFH
- Housing is not provided
- Health insurance is not provided for interns
- Final offer amounts are determined by multiple factors, including experience and expertise, and may vary
- Outstanding performers might be offered a full-time position at the end of the program