Staff / Senior Staff AI Infra Engineer (Inference Infrastructure)

Together Computer Inc; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Health insurance

Retirement plan

Dental insurance

Vision insurance

401(k) plan

Short-term disability

Long-term disability

Life insurance

AD&D insurance

Commuting stipend

Team events

Flexible time off

Team lunches

Job summary

Together Computer Inc. is seeking a reliability-minded software engineer to own the production lifecycle of the GPU inference fleet and the Kubernetes‑native control plane that provisions clusters, models, and capacity.

You will triage InfiniBand/RDMA issues and extend automated self‑healing to reduce outages across fleet scale. You’ll own SLOs and error budgets for inference serving, drive incident response, and translate postmortems into durable improvements in controllers, automation, and

Qualifications

• Deep experience owning production reliability for large‑scale distributed systems.
• Hands-on Kubernetes controller/CRD patterns and remediation systems.
• Experience with multi‑tenant model serving and with running differentiated SLOs across model pools.

Responsibilities

• Own SLOs and error budgets for inference serving.
• Lead incident response and postmortems; drive systemic fixes into controllers and automation.
• Extend automated self‑healing; add detection/remediation plugins for new failure modes.
• Triage and fix production issues across fleet scale; translate failures into design improvements.

Skills

Kubernetes controllers

CRD patterns

Reconciliation loops

Observability focus

Event-driven design

Infra as software

SRE production reliability

Root cause analysis

Tools

InfiniBand/RDMA tooling

GPU/ML serving tooling

Monitoring stacks

Job description

• We’re looking for a software engineer, reliability‑minded but still a builder, to own what happens in production to the Kubernetes‑native control plane that provisions and runs our GPU inference fleet
• The platform team builds the manifest‑driven API and controllers that let the inference team declare what they need, a cluster, a model deployment, a capacity change, and get it reconciled underneath
• Your job is to keep that promise true in the real world: triaging InfiniBand issues when prefill and decode nodes stall exchanging KV cache over RDMA, diagnosing hero‑model and LoRA‑serving faults that don’t show up in generic health checks, and extending the automated self‑healing system so each new failure mode becomes a permanent fix instead of a recurring page
• The core value we’re after is keeping the decoupling real even when things break, and keeping the fleet efficient without that efficiency becoming a new source of instability
• You’ll own SLOs and error budgets for inference serving, lead incident response, and turn what postmortems teach you into actual changes in the controllers and automation, not just updated runbooks
• You’ll also work the reliability side of capacity efficiency, since a mistuned defragmentation or bin‑packing pass is itself a production risk
• Strong candidates have hands‑on production‑reliability experience on large‑scale distributed or GPU‑serving systems, are comfortable troubleshooting InfiniBand/RDMA and Kubernetes controller/CRD‑based platforms, and think about GPU infrastructure, and the tools that keep it reliable, as software to be engineered
• A product mindset applies: the on‑call experience, the clarity of an alert, and the judgment built into an automated remediation are things you ship and iterate on
• Operate the provisioning state machine in production: own the health of the host lifecycle pipeline, discovery, inference bring‑up, GPU driver/CUDA validation, health checks, decommission/RMA, triaging stuck or failed state transitions at fleet scale and feeding real failure patterns back into how the states and transitions are designed
• Triage and extend automated self‑healing: when the node‑scanning and remediation platform misses something, a new failure mode, an InfiniBand issue in disaggregated prefill/decode serving, a GPU Xid variant, a hero‑model or LoRA‑specific fault, diagnose it live, drive the fix to production, and turn it into a new detection/remediation plugin so it’s automatic the next time
• Own end‑to‑end reliability of the pipeline: hold the SLOs and error budgets for provisioning and fleet health, lead incident response when idempotency, retry, rollback, or drift assumptions break down in practice, and drive the systemic fix, not just the hotfix
• Partner with the inference/ML platform team from the production side: be the one who knows how real cluster topologies, interconnects, and scheduling constraints actually fail in the field, and feed those failure modes back as first‑class requirements into the platform’s abstractions
• Work alongside machine learning researchers, engineers, and product managers to bring our latest technologies into production, enabling advanced research through awesome engineering
• Introduce new techniques, tools, and architecture that improve the performance, latency, throughput, and efficiency of our model inference stack
• Build tools to give us visibility into our bottlenecks and sources of instability, then design and implement solutions to address the highest‑priority issues
• Lead reliability cross‑functionally: build coalition across infra, ML platform, and product teams around shared reliability priorities, manage stakeholders through incidents and roadmap trade‑offs, and represent the reliability point of view in planning so it shapes decisions before they ship, not after an outage

Benefits

• Competitive health insurance plans
• Income protection & retirement
• Dental and vision insurance
• Pre‑tax flexible spending accounts
• Mental health support and services
• 401(k) plan
• STD & LTD insurance
• Life insurance
• AD&D insurance
• Monthly commuting stipend + pre‑tax bene
• Team‑driven celebrations and events
• Flexible time off policy
• Monthly team lunches

A demonstrated track record of eliminating operational toil through automation and tooling you built yourself, not just process or documentationDeep experience owning production reliability for large‑scale distributed systems; GPU/ML‑serving infrastructure experience is a strong plusHands‑on experience with Kubernetes controller/CRD patterns, reconciliation loops, and node‑level health/remediation systemsFamiliarity with the operational realities of multi‑tenant model serving (LoRA/adapter‑based serving) and with running differentiated SLOs across model pools of different priorityComfort with event‑driven architectures, backpressure/circuit‑breaking design, and treating observability (metrics, logs, traces) as something built into a system, not added after an incidentExperience operating a provisioning or host‑lifecycle pipeline in production, comfortable troubleshooting stuck or failed state transitions (discovery, bring‑up, GPU driver/CUDA validation, health checks, decommission/RMA) at fleet scale, and translating real failure patterns back into improvements to the state machine’s designA software‑engineering mindset first: you write and ship production code, and you think about GPU infrastructure as software to be engineered, not a fleet to be manually operatedHands‑on experience troubleshooting InfiniBand/RDMA networking issues, ideally in a multi‑node training or disaggregated‑inference context — comfortable reading IB port counters and subnet manager logs, not just application metrics