We are seeking an experienced ML Systems Engineer to join a dynamic team focused on building simulation environments where AI models learn to build and optimize inference systems.
Key Responsibilities:
- Integrate machine learning models into real serving codebases, identify bottlenecks, implement fixes, and demonstrate performance improvements without altering output results.
- Take full ownership of tasks end to end, including the environment setup, verification processes, and quality assurance.
- Collaborate remotely within India.
Ideal Candidate Profile:
- 3 to 6 years of experience running ML inference in production environments.
- Strong ownership of latency, throughput, and memory optimization.
- Deep knowledge of batching strategies, key-value caching, parallelism, kernel optimization, and quantization techniques.
Location: Remote (India)
Compensation: 30 - 60 LPA
