GURUGRAM · FULLTIME
GPU Performance Engineer
CredFlow
Gurugram · onsite · Posted 76d ago
Sourced from
Not disclosed3–6 yrsfulltimeGurugram
About a minute. You'll make an account on the way through.
agent · working
- Read this posting0.6s
- Found the form on Instahyre · 13 questions to answer1.8s
- Decided the answers for all of them3.2s
- Tailor your résumé to this role
- Waiting for you
Section · 01
About this role
Requirements:
- 5+ years in systems, HPC, distributed systems, or ML infrastructure.
- Hands-on experience with AI inference serving.
- Strong Python; working knowledge of C++/CUDA.
- Experience with multi-node GPU clusters and containerized deployments.
- Benchmark-driven, performance optimization mindset.
- Ability to work independently with weekly checkpoints.
Nice to Have:
- Quantized inference (FP8/FP4).
- KV transfer/cache-tiering projects.
- Open-source contributions (vLLM, SGLang, etc. ).
- Bayesian optimization or autotuning experience,
Sourced from instahyre
Section · 02
Skills
CudaComputer VisionPythonGenerative AiMachine LearningdistributedHpcSystemsGPUinferenceInfrastructure
Section · Company
About CredFlow
CredFlow
Internet
2019
7 years old
Delhi,NCT
India
₹5.4L PA avg
Avg at CredFlow
About
CredFlow provides financial solutions to automate your cashflows. Credflow is a vertical specific cashflow management solution that leverages technology to build customized credit solutions and automate receivable collections. Credflow has the vision to revolutionize credit flow through the supply chain to help businesses grow exponentially - one vertical at a time. Credflow was founded in 2019 and is located in New Delhi, India.
Industries
InternetFinancial Services
Employee ratings
10 reviews
3.1/ 5
Culture
2.5
Career growth
2.3
Work-life
2.3
Employees rate it well for
Compensation & Benefits32Overall Company31
Find them on