---
title: '(Senior/Junior AI Inference Reliability Engineer, Compute Infra at Together AI'
canonical: 'https://feeny.ai/job/senior-junior-ai-inference-reliability-engineer-compute-infra-together-ai-san-ezx2bg8b6zje'
type: 'job'
last_seen: '2026-11-06'
---

# (Senior/Junior AI Inference Reliability Engineer, Compute Infra at Together AI

- **Company:** Together AI
- **Location:** San Francisco, CA
- **Posted:** 2026-10-27
- **Last confirmed live:** 2026-11-06
- **Apply:** https://job-boards.greenhouse.io/togetherai/jobs/5268939007

## Job description

## About the Role

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.

## Responsibilities

- 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.

## Requirements

- Experience 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 design.
- Deep experience owning production reliability for large-scale distributed systems; GPU/ML-serving infrastructure experience is a strong plus.
- Hands-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.
- Familiarity with the operational realities of multi-tenant model serving (LoRA/adapter-based serving) and with running differentiated SLOs across model pools of different priority.
- A demonstrated track record of eliminating operational toil through automation and tooling you built yourself, not just process or documentation.
- Hands-on experience with Kubernetes controller/CRD patterns, reconciliation loops, and node-level health/remediation systems.
- Comfort with event-driven architectures, backpressure/circuit-breaking design, and treating observability (metrics, logs, traces) as something built into a system, not added after an incident.
- A 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 operated.

## About Together AI

Together AI, the AI Native Cloud, is purpose-built for AI engineers. AI application developers get high-performance inference that scales reliably, fine-tuning and reinforcement learning for creating frontier-level specialized models, and pre-training at massive scale for fully custom intelligence, all around a marketplace of leading open models that teams can run, adapt, and own. Trusted by Cursor, Decagon, ElevenLabs, Salesforce, and Zoom, Together serves 400+ trillion tokens a month.

## Compensation

We offer competitive compensation, startup equity, health insurance and other competitive benefits. The US base salary range for this full-time position is: $160,000 - $280,000 + equity + benefits. Our salary ranges are determined by location, level and role. Individual compensation will be determined by experience, skills, and job-related knowledge.

Application Policy

Please read each role carefully and apply to the position best suited to you. Candidates are limited to 6 applications within a 90-day period, and applications beyond that limit will be automatically rejected. You may apply to additional roles 90 days after your last application.

## Equal Opportunity

Together AI is an Equal Opportunity Employer and is proud to offer equal employment opportunity to everyone regardless of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, veteran status, and more.

Please see our privacy policy at https://www.together.ai/privacy.

## About Together AI

## Company Overview
- **One-liner**: Together AI is the AI Native Cloud, a full-stack platform for production AI that provides inference, fine-tuning, and GPU compute powered by cutting-edge systems research.
- **Entity Type**: Private (Series C)
- **Headquarters**: San Francisco, California, United States
- **Founded**: 2022
- **Founders**: Vipul Ved Prakash (CEO), Ce Zhang (CTO), Tri Dao (Chief Scientist), Chris Ré, Percy Liang

## Core Business
- **Primary industry**: AI Infrastructure / Cloud Computing
- **Target customers**: B2B – AI-native startups (e.g., Cursor, Decagon, Eleven Labs), enterprise SaaS (Salesforce, Zoom, Zomato), and AI researchers.
- **Mission**: “Significantly lower the cost of modern AI systems by co-designing software, hardware, algorithms, and models” — with a commitment to open and transparent AI development.

## Products & Services
- **Serverless Inference**: Fast on-demand inference for open-source models with no infrastructure management.
- **Batch Inference**: Asynchronous processing of massive workloads (up to 30B tokens per model) at reduced cost.
- **Dedicated Model Inference**: Deploy models on dedicated GPU infrastructure for speed and control.
- **Dedicated Container Inference**: GPU infrastructure optimized for generative media (video, audio, image).
- **Fine-Tuning**: Fine-tune open-source models using latest research techniques (improves accuracy, reduces hallucinations).
- **Accelerated Compute**: Self-serve instant clusters to thousands of GPUs, optimized with Together Kernel Collection.
- **Model Shaping**: Tools to accelerate inference, model shaping, and pre-training.
- **Managed Storage**: High-performance object storage and parallel filesystems with zero egress fees.
- **Sandbox**: Fast, secure code sandboxes for AI app/agent development environments.

## Market Standing
- **Valuation/Market Cap**: Not publicly disclosed; recent Series C reportedly doubled valuation (amount undisclosed) [cbinsights.com](https://www.cbinsights.com/company/together-4)
- **Key Metric**: **Total Funding** – $1.334B (including $800M Series C announced in mid-2026) [cbinsights.com](https://www.cbinsights.com/company/together-4)
- **Notable Investors/Partners**: Kleiner Perkins, NVIDIA, Salesforce Ventures, Prosperity7 Ventures (Aramco), and 29+ others across rounds.
- **Growth Signals**: 
  - Headcount grew 91% YoY to ~280 employees [linkedin.com](https://www.linkedin.com/company/togethercomputer)
  - Acquired CodeSandbox (Dec 2024) and Refuel.AI (May 2025)
  - Customers include Cursor, Decagon, Eleven Labs, AI21, Hedra, Cartesia, Salesforce, Zoom, Zomato
  - Published nine papers at ICML 2026; open-sourced ParallelKernelBench

## Competitive Advantages
- **Full-stack AI platform** covering inference, fine-tuning, compute, storage, and sandboxes — all integrated.
- **World-class research team** co-designing algorithms, kernels, and hardware (e.g., Tri Dao, co-inventor of FlashAttention).
- **Open-source commitment** and contributions (models, datasets, research) build developer trust and ecosystem lock-in.
- **Cost performance**: Claims 2x faster inference and 60% lower cost vs. alternatives through research-driven optimizations.

## Strategic Focus
- Accelerate the shift to open-source AI by making it economically viable at scale.
- Continue investing in systems research (GPU programming, kernel optimization, model shaping) to improve performance and cost.
- Expand enterprise adoption through dedicated deployments and partnerships.
- Grow the platform’s capabilities (e.g., managed storage, sandboxes) to reduce friction for AI-native builders.

## Why Work Here
- **Culture**: Values include “Do more with less,” “Open and responsible development,” “Empower innovation,” and “Optimizers” — a research-driven, mission-oriented environment.
- **Remote/Hybrid/Office**: Primarily office-based in San Francisco (251 Rhode Island Street) with employees across 16 countries. Office perks include lunch, dinner, snacks, parking/transit stipends, and relocation support.
- **Benefits**: Competitive salary and equity, 401K matching, health/dental/vision insurance, flexible PTO, generous parental leave, life and disability protection.
- **Engineering Culture**: Deep focus on systems research and open-source; engineers work alongside leading AI researchers (e.g., Tri Dao, Ce Zhang). Talent sourced from Apple, Google, Amazon, NVIDIA, Stanford AI Lab.
- **Career Growth**: 53 active job postings (as of mid-2026); roles span ML engineering, platform engineering, research, and go-to-market. High growth trajectory offers rapid advancement.

## Sources
1. [together.ai/about-us](https://www.together.ai/about-us)
2. [together.ai/](https://www.together.ai/)
3. [together.ai/careers](https://www.together.ai/careers)
4. [linkedin.com/company/togethercomputer](https://www.linkedin.com/company/togethercomputer)
5. [cbinsights.com/company/together-4](https://www.cbinsights.com/company/together-4)

## Other roles at Together AI

- [Sr. Field Marketing & Community Manager](https://feeny.ai/job/sr-field-marketing-community-manager-together-ai-new-york-ktvpck67xssg) — New York, NY
- [Sr. Field Marketing & Community Manager, EMEA](https://feeny.ai/job/sr-field-marketing-community-manager-emea-together-ai-london-zv31yqscs4zq) — London, United Kingdom
- [Event & Field Marketing Specialist](https://feeny.ai/job/event-field-marketing-specialist-together-ai-san-francisco-nge6b7exjfwk) — San Francisco, CA
- [Senior Recruiter, G&A](https://feeny.ai/job/senior-recruiter-g-a-together-ai-san-francisco-h3zvr47skd5r) — San Francisco, CA
- [Technical Writer Intern, Developer Experience (Summer 2027)](https://feeny.ai/job/technical-writer-intern-developer-experience-summer-2027-together-ai-san-sahqq9k7yvzx) — San Francisco, CA
- [Director, Debt Capital Markets](https://feeny.ai/job/director-debt-capital-markets-together-ai-san-francisco-7ryc68dwe7h0) — San Francisco, CA
- [Forward Deployed Engineer, Post-Training](https://feeny.ai/job/forward-deployed-engineer-post-training-together-ai-san-francisco-57ckxj1h1nmb) — San Francisco, CA
- [Growth Marketing Intern (Summer 2027)](https://feeny.ai/job/growth-marketing-intern-summer-2027-together-ai-san-francisco-m075apmcwsef) — San Francisco, CA
- [Senior Counsel - Product & Privacy](https://feeny.ai/job/senior-counsel-product-privacy-together-ai-san-francisco-ng1h3afr2n1z) — San Francisco, CA
- [(Staff / Senior Staff) AI Inference Reliability Engineer, Compute Infra](https://feeny.ai/job/staff-senior-staff-ai-inference-reliability-engineer-compute-infra-together-ai-2j57agj7vfjh) — San Francisco, CA