Company
Technology
SeniorMLEngineer(TokenFactory)
“Senior ML Engineer (Token Factory). Skills: ML Engineering, LLM Optimization, GPU Computing. Drive inference optimization efforts. Identify bottlenecks”
What You'll Achieve.
Improve throughput; Reduce latency; Reduce cost per token
Industry & Context.
Root cause analysis; Performance analysis
What They're Looking For.
Must Have
Understanding of machine learning fundamentals, Transformer architectures, Large language models, Profiling and optimizing GPU workloads, Nsight or PyTorch Profiler, Deep knowledge of GPU architecture, Memory hierarchy, Compute vs. memory trade-offs, Key LLM concepts, Attention mechanisms, RoPE, KV-cache, Flash Attention, Quantization techniques, Large-scale deep learning training, Distributed systems, Sharding strategies, Custom kernel development, Software engineering skills, Advanced proficiency in Python, Modern ML frameworks, Solid understanding of software engineering practices, Version control, CI/CD pipelines, Unit testing
Nice to Have
FP8, MXFP4 training/inference pipelines, Hardware-aware optimizations
What You'll Do.
Drive inference optimization efforts
Implement performance improvements
Reduce cost per token
Contribute to inference engine design
Contribute to inference engine evolution
Develop low-precision training pipelines
Develop low-precision inference pipelines
Productionize low-precision training pipelines
Productionize low-precision inference pipelines
Profile GPU workloads
Analyze GPU workloads
Identify performance constraints
Guide architectural improvements
Collaborate on distributed training systems
Collaborate on distributed inference systems
Contribute to engineering best practices
Contribute to testing
Contribute to maintainable ML systems
How You'll Work.
Team & Collaboration
Cross-functional teams
Communication Scope
Technical communication
Process & Methodology
CI/CD
Applying for this Senior ML Engineer (Token Factory) role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Lever
- Lever uses a streamlined one-page form — apply in under 5 minutes.
- LinkedIn import works well; review parsed data before submitting.
- The cover letter field is optional but visible to reviewers — use it to differentiate.
- Referral codes from employees can significantly boost visibility of your application.
ANONYMOUS · UNFILTERED
What do employees actually say about this company?
Real rants from real employees. Read before you apply.