Site Reliability Engineer at Simplismart
Why it's worth a look: Work on production infrastructure powering GenAI inference, focusing on Kubernetes, scaling, observability, and GPU workloads in Bengaluru.
The founder's post on X
We're hiring a Site Reliability Engineer (SRE) at Simplismart in Bengaluru! You'll work on the infrastructure powering GenAI inference, tackling real production challenges around reliability, Kubernetes, scaling, observability, and GPU workloads. → 2+ YoE [skill matters more…
About the role
Improve platform reliability, scaling, observability, and operational excellence for Simplismart's high-throughput multi-cloud/on-prem GenAI inference infrastructure and GPU clusters.
What you'd do
- Maintain platform service uptime, reliability, and performance across production environments
- Manage Kubernetes clusters and cloud infrastructure across AWS, GCP, and Azure
- Build incident response workflows, on-call schedules, root cause analyses (RCAs), and deployment rollback strategies
- Build and maintain monitoring, alerting, and operational dashboards (Prometheus, Grafana Cloud)
- Automate deployment, auto-scaling, and operational workflows with Terraform, Helm, and CI/CD pipelines
- Troubleshoot production incidents across AI model serving runtimes and GPU infrastructure
What they're looking for
- 2+ years of experience in SRE, DevOps, or Platform Engineering roles
- Strong hands-on knowledge of Linux systems, networking, and Kubernetes
- Hands-on experience with cloud providers (AWS, GCP, or Azure)
- Proficiency with Terraform, Helm, and CI/CD pipelines
- Scripting proficiency in Python, Bash, or Go
- Demonstrated incident management and troubleshooting skills
Nice to have
- Experience with MLOps or AI inference infrastructure
- Hands-on exposure to GPU clusters and model serving systems (Triton, vLLM, TensorRT-LLM)
- Experience with release engineering and strict enterprise SLA reliability
Gathered from the founder's post and the company's public pages.
Terms
- Location
- Bengaluru
- Remote
- On-site
- Salary
- Competitive base + ESOPs (unspecified exact figure)From the company's pages, not the post
- Equity
- Not mentioned in the post
Ask the founder
The company
Simplismart
High-performance GenAI inference engine and orchestration platform for enterprise AI deployments.
Simplismart builds an MLOps and inference platform that enables engineering teams to deploy, fine-tune, auto-scale, and monitor generative AI models (LLMs, speech, vision, diffusion) across public cloud and on-premises environments. Its engine features custom kernel optimizations, sub-minute autoscaling, and fractional GPU sharing to slash inference latency and cloud compute costs.
Customers: Tata 1mg, Physics Wallah, Sanas, Invideo, Ema, and Dashtoon.
- Stage
- Series A
- Funding
- Series A · $7,000,000 · 2024-10
- Team size
- 40-60 employees
- Based in
- Bengaluru, India
- Founded
- 2022
Funding
- Series A · $7,000,000 · 2024-10 · Accel, Shastra VC, Titan Capital, Akshay Kothari (Co-founder of Notion)forbes.com
- Seed · ~$1,300,000 · 2023 · Titan Capital, Angel Investorswellfound.com
People
- Amritanshu Jain · Co-founder & CEOEx-Cloud Infrastructure Engineer at Oracle Cloud.simplismart.ai
- Devansh Ghatak · Co-founder & CTOFormer Search Engineer at Google.simplismart.ai
Our research
What we found
- Simplismart raised a $7M Series A led by Accel in October 2024, bringing total funding to over $8M.forbes.com
- The platform focuses on low-latency, cost-effective inference for LLMs, speech, and diffusion models across cloud and on-prem hardware.simplismart.ai
- Co-founders are technical operators coming from Oracle Cloud and Google Search.simplismart.ai
- The job poster is Aditya Krishnan, a Senior Cloud Infrastructure Engineer at Simplismart recruiting for his infrastructure team.theorg.com
Our read
- Stage
- Series ABased on: Raised $7M Series A led by Accel in October 2024.
- Team size
- 40-60 employeesBased on: Reported 43 members on TheOrg and 51-200 bracket on Wellfound.
- Engineer number
- 15-25 engineersBased on: Estimated breakdown from team directory and current hiring volume.
- Salary range
- ₹18,00,000 – ₹35,00,000 INR / yearBased on: Market rates for 2+ YoE SRE/DevOps at top venture-backed Series A startups in Bengaluru.
- Equity range
- 0.05% – 0.20%Based on: Standard Series A equity grant for early-to-mid career platform/SRE engineers.
- Runway signal
- Strong (24+ months)Based on: $7M Series A closed recently in late 2024 with a lean India-based engineering team.
Estimates from public information, not confirmed by the company.
Worth asking the founder
- What is the current scale of the GPU cluster fleet (number of nodes and cloud vs on-prem split)?
- What does the on-call rotation cadence look like for the SRE team?
- How closely does this SRE role interact with the model optimization and CUDA runtime engineers?
How it works
- 1You write to the founderEmail or reply on X. Your words, your call — no form, no review.
- 2It reaches them directlyStraight to their inbox or their post. We're not in the thread.
- 3Got an offer? Tell usIt's how we know this works.
Founders reply to specifics: what you've built, a link, and why this role.