This role is for one of Weekday’s clients
Min Experience: 5+ years
Location: NCR, Gurgaon, Haryana, India
JobType: full-time
We are looking for an exceptional Founding Platform Engineer with deep expertise in Site Reliability Engineering (SRE), DevOps, cloud infrastructure, and production Machine Learning (ML) systems.
In this high-ownership role, you will architect, build, and operate the core platform infrastructure supporting large-scale AI-powered applications. You will own critical infrastructure components across cloud architecture, production ML deployment, distributed systems, observability, security, and reliability.
You will work closely with the founding team and AI/ML engineers to build scalable, secure, and resilient infrastructure capable of supporting millions of users, high-concurrency workloads, and mission-critical AI operations.
A key requirement is direct ownership of at least one production-grade ML system, including its deployment, monitoring, scaling, and operational reliability.
Requirements
Key Responsibilities
Cloud Infrastructure & Platform Engineering
•Architect, build, and operate scalable, secure, and highly available cloud infrastructure, primarily on AWS.
•Design and manage containerised workloads using Kubernetes, Amazon ECS, and Docker.
•Implement Infrastructure as Code (IaC) using Terraform, AWS CDK, or equivalent tools.
•Build and maintain robust CI/CD pipelines, automated deployment workflows, and safe rollback mechanisms.
•Design infrastructure capable of supporting millions of users and large-scale concurrent workloads.
•Optimise cloud infrastructure for performance, scalability, availability, and cost efficiency.
Production ML Infrastructure & Reliability
•Own the deployment, scalability, availability, and operational reliability of mission-critical machine learning systems.
•Build and maintain infrastructure for production ML inference workloads, including Large Language Models (LLMs) and speech models.
•Manage GPU-based infrastructure, model-serving services, inference workloads, and execution orchestration.
•Optimise model-serving infrastructure for latency, throughput, reliability, and cost.
•Establish monitoring, recovery, and uptime standards for production ML systems.
•Collaborate with AI/ML engineers to support model deployment, infrastructure requirements, and production performance.
Data Engineering & Distributed Systems
•Design and maintain reliable data infrastructure, including databases, message queues, streaming systems, and distributed workers.
•Work with technologies such as PostgreSQL, Redis, Kafka, and other distributed data-processing systems.
•Build scalable data pipelines supporting ML inference, application services, and operational workloads.
•Ensure data consistency, fault tolerance, and efficient processing across distributed environments.
•Design and maintain reliable asynchronous processing and high-concurrency systems.
Site Reliability Engineering & Observability
•Establish end-to-end observability across infrastructure, application services, and ML workloads.
•Implement monitoring, logging, distributed tracing, alerting, and incident-response frameworks.
•Define and manage Service Level Indicators (SLIs), Service Level Objectives (SLOs), and operational reliability standards.
•Own production incident management, root-cause analysis, and post-incident improvements.
•Identify infrastructure bottlenecks and proactively eliminate recurring reliability issues.
•Build automation to improve system availability, operational efficiency, and recovery capabilities.
Infrastructure Security & Scalability
•Design secure infrastructure for sensitive user data, credentials, payments, and AI-agent operations.
•Implement Identity and Access Management (IAM), secrets management, network isolation, access controls, and infrastructure hardening.
•Architect isolated execution environments for concurrent AI agents and browser-based workloads.
•Ensure secure and fault-tolerant execution of long-running workflows and critical transactions.
•Establish infrastructure security practices that support scalability, resilience, and data protection.
Required Qualifications
•5+ years of hands-on experience in Site Reliability Engineering, DevOps, Infrastructure Engineering, or Platform Engineering.
•Direct ownership of at least one mission-critical, production-grade ML system, including deployment, monitoring, scaling, and operational reliability.
•Exceptional understanding of AWS cloud infrastructure, including networking, compute, storage, security, and distributed systems.
•Strong hands-on expertise with Kubernetes, ECS, Docker, Terraform or AWS CDK, and CI/CD pipelines.
•Strong understanding of data engineering fundamentals, including data pipelines, databases, messaging systems, and distributed processing.
•Experience operating highly available, low-latency production systems at meaningful scale.
•Proven ability to troubleshoot complex infrastructure issues and independently lead production incident resolution.
•Strong automation and scripting capabilities using Python, Bash, or similar languages.
•Ability to independently architect, build, and own infrastructure in a fast-paced startup environment.
Preferred Qualifications
•Experience managing GPU infrastructure and production LLM/ML inference systems.
•Exposure to model-serving technologies such as vLLM, NVIDIA Triton, or equivalent platforms.
•Experience with real-time voice AI, speech processing, or latency-sensitive inference workloads.
•Experience scaling high-concurrency systems, long-running workers, or isolated execution environments.
•Background in high-scale AI/ML product companies, fintech platforms, or infrastructure-intensive SaaS businesses.
•Experience building platform infrastructure from scratch or working as an early infrastructure engineering hire.
Must-Have Skills
•Site Reliability Engineering (SRE)
•DevOps
•AWS Cloud Infrastructure
Good-to-Have Skills
•GPU Infrastructure
•LLM Inference
•Speech Models