BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201224Z
LOCATION:Hall 6
DTSTART;TZID=America/Chicago:20251117T165100
DTEND;TZID=America/Chicago:20251117T165100
UID:submissions.supercomputing.org_SC25_sess553_job284@linklings.com
SUMMARY:Staff Production Engineer
DESCRIPTION:Mission:\nJoin the team that builds and operates Groq’s real-t
 ime, distributed inference system delivering large-scale inference for LLM
 s and next-gen AI applications at ultra-low latency. As a Low-Level Produc
 tion Engineer, your mission is to ensure reliability, fault tolerance, and
  operational excellence in Groq’s LPU-powered infrastructure. You’ll work 
 deep in the stack—bridging distributed runtime systems with the hardware—t
 o keep Groq systems fast, stable, and production-ready at scale.\n\nRespon
 sibilities & opportunities in this role:\nProduction Reliability: Operate 
 and harden Groq’s distributed runtime across thousands of LPUs, ensuring u
 ptime and resilience under dynamic global workloads.\nLow-Level Debugging:
  Diagnose and resolve hardware-software integration issues in live environ
 ments, from datacenter level events to single component failures.\nObserva
 bility & Diagnostics: Build tools and infrastructure to improve real-time 
 system monitoring, fault detection, and SLO tracking.\nAutomation & Scale:
  Automate deployment workflows, failover systems, and operational playbook
 s to reduce overhead and accelerate reliability improvements.\nPerformance
  & Optimization: Profile and tune production systems for throughput, laten
 cy, and determinism—every cycle counts.\nCross-Functional Collaboration: P
 artner with compiler, hardware, infra, and data center teams to deliver ro
 bust, fault-tolerant production systems.\n\nIdeal candidates have/are:\nPr
 oven experience in production engineering across the stack and operating l
 arge-scale distributed systems.\nDeep knowledge of computer architecture, 
 operating systems, and hardware-software interfaces.\nSkilled in low-level
  systems programming (C/C++ or Rust), with scripting fluency (Python, Bash
 , or Go).\nComfortable debugging complex issues close to the metal—kernels
 , firmware, or hardware-aware code paths.\nStrong background in automation
 , CI/CD, and building reliable systems that scale.\nThrive across environm
 ents—from kernel internals to distributed runtimes to data center operatio
 ns.\nCommunicate clearly, make pragmatic decisions, and take ownership of 
 long-term outcomes.\n\nNice to have:\nExperience operating high-performanc
 e, real-time systems at scale (ML inference, HPC, or similar).\nFamiliarit
 y with GPUs, FPGAs, or ASICs in production environments.\nPrior exposure t
 o ML frameworks (e.g., PyTorch) or compiler tooling (e.g., MLIR).\nTrack r
 ecord of delivering complex production systems in high-impact environments
 .\n\nAttributes of a Groqster:\nHumility – Egos are checked at the door\nC
 ollaborative & Team Savvy – We make up the smartest person in the room, to
 gether\nGrowth & Giver Mindset – Learn it all versus know it all, we share
  knowledge generously\nCurious & Innovative – Take a creative approach to 
 projects, problems, and design\nPassion, Grit, & Boldness – No-limit think
 ing, fueling informed risk taking\n\nRegistration Category: Technical Prog
 ram Reg Pass, Workshop Reg Pass, Tutorial Reg Pass, Exhibits Reg Pass\n\nC
 ountry: United States of America\n\nCompany: Groq\n\nIn-Person / Remote: R
 emote\n\nPart Time / Full Time: Full Time\n\nPosition Type: Permanent\n\n
END:VEVENT
END:VCALENDAR