NVIDIA · Primly Community

went through the NVIDIA inference infra loop last month, here's what actually happened

infra_ines · 5 replies

applied for a senior ML infra role on the inference optimization team. six rounds total over 3.5 weeks.

recruiter screen: standard 30 min, mostly comp alignment and why NVIDIA. pretty smooth.

phone tech: this was heavier than expected. 90 minutes, two interviewers, one LC problem (graph traversal, medium-ish) and then a bunch of questions about CUDA memory hierarchy. like actual questions: what's the difference between global and shared memory, what happens when you have warp divergence, how do you profile a CUDA kernel. i am not a CUDA expert so i was honest about the gaps and talked through my reasoning. they seemed fine with that.

virtual onsite: 5 back-to-back sessions. coding: two more LC problems, one tree, one DP. nothing brutal but you have to be fast. system design: design a serving system for a large language model at 50k QPS. we talked about batching strategies, KV cache management, load balancing across GPUs. this was the most interesting round honestly. ML depth: transformer internals, quantization tradeoffs, RLHF from a training infra angle. cross-functional: a PM and a TPM. behavioral + how do you work with people who don't speak your language. hiring manager: 45 min, went deep on past projects, what i own vs what i just contributed to.

overall: they want people who can go deep and who have genuine opinions. if you're vague about how something works they'll notice. i got an offer at L5, Santa Clara based.

5 replies

infra_ines

the CUDA memory hierarchy question in a phone screen is very NVIDIA. did they actually care about the answer or were they testing whether you'd panic?

ml_mike

both, i think. i stumbled a bit on warp divergence and they walked me through it rather than cutting me off. felt like they were testing floor, not ceiling. but if you have zero GPU background i'd do some prep before that round.

remote_swe_42

L5 offer, Santa Clara. curious what comp looked like if you're open to sharing. NVIDIA's RSU refresh is supposedly strong but the base has been oddly flat for IC roles.

corp_refugee

90 minute phone screen with two interviewers is a lot. some companies do this as a de facto first onsite. did you know going in that it would be that long?

ml_mike

recruiter said 60 min. it ran over. classic.