Pranay Singh Parihar
Contact details — on requestProof of Work — on request
Experience
Founder
Inferno · Jan 2026 – Present
- • Built InfernoRT, an AI inference runtime that outperforms llama.cpp across every benchmark configuration where both runtimes successfully complete execution.
- • Enabled workloads that fail on other runtimes due to memory constraints, including 8B-class models within a 4 GB RAM budget and 70B-class models within 16 GB RAM.
- • Delivered higher decode throughput and lower time-to-first-token than other runtimes while preserving output correctness under our validated benchmark suite.
- • Achieved almost 2x the imporvements in TTFT than llama.cpp
- • Built a production benchmarking framework spanning 480 workloads to validate latency, throughput, correctness, and memory behavior against the industry baseline.
- • Filed core IP for deterministic memory management enabling efficient local AI inference.
Project Lead
NCR Atleos · Mar 2023 – Present
- • Architected an autonomous agent system leveraging LLM-based decision trees to orchestrate DevOps workflows across AWS environments.
- • Implemented event-driven AI agents with specialized roles (monitoring, deployment, security) using asynchronous messaging via Amazon SQS and EventBridge.
- • Engineered bidirectional API interfaces between agentic systems and CI/CD pipelines using OAuth2 and JWT for secure authentication.
- • Provisioned AWS infrastructure using Terraform with remote state stored in S3 and access controlled via IAM roles and policies.
- • Implemented multi-stage Docker builds with optimized layer caching, reducing image size by 76%.
- • Deployed containerized applications on Amazon EKS with Horizontal Pod Autoscaling based on CloudWatch metrics (CPU/memory).
- • Configured Amazon CloudFront with AWS WAF for edge security and global content delivery.
- • Implemented GitOps workflow using Flux CD with automated Kubernetes manifest generation for EKS.
- • Developed RESTful API connectors for bidirectional data exchange with Artifactory, GitHub, Atlassian,SonarQube, Mend, Seeker, and Coverity.
- • Built an OAuth2 token management system with automatic refresh and secure credential rotation using AWS Secrets Manager.
- • Created standardized webhook listeners using API Gateway and Lambda for real-time event processing across integrated platforms.
- • Engineered a unified query language translator for aggregating and normalizing data across DevOps tools.
- • Integrated enterprise SSO using AWS SSO with SAML 2.0, enabling JIT provisioning and role-based access control.
- • Designed a least-privilege IAM policy framework with granular permissions and automated audits.
- • Integrated Trivy into CI pipelines for automated container vulnerability scanning.
- • Secured communication channels using TLS 1.3 with perfect forward secrecy across all services.
Insurjo'22 Cohort Member
Insurjo · Sep 2022 – Present
DevOps Engineer
NCR Corporation · Dec 2021 – Present
- Enabled AWS Cloudtrail across all AWS accounts to log all API calls, ensuring complete visibility into user activities and service interactions.
- Configure trails to deliver log files to an S3 bucket for storage.
- • Deployed AWS Config using Terraform to continuously monitor and record AWS resource Configurations.
- Utilized Ansible playbooks to enforce compliance policies by creating and managing AWS Config rules that ensure resources like S3 buckets and EC2 instances adhere to security standards.
- • Integrated AWS Config with Cloudwatch Events using Terraform to trigger immediate compliance checks and remediation action via AWS Lambda.
- Developed Lambda functions to automatically apply encryption to unencrypted S3 buckets detected by Config rules.
- • Implemented CloudWatch metric filters to parse CloudTrail logs for specific events such as unauthorized API calls and IAM policy changes.
- Configured CloudWatch alarms to notify the security team when predefined thresholds were breached.
- • Developed AWS Lambda functions to respond to CloudWatch alarms and Config rule violations.
- • Configured Amazon SNS topics to send real-time notifications to security and operations teams, Integrated SNS with communication tools like Slack and email for alert dissemination.
- •Enabled AWS GuardDuty to continuously analyze VPC Flow logs, CloudTrail logs, and DNS logs for signs of malicious activity.
- • Setup CI/CD pipeline using GitHub Actions and Jenkins to automate the deployment of Terraform scripts, ansible playbook and Lambda function code, ensuring consistent and reliable updates to the auditing and alerting system.
- • Implemented dynamic inventory management in Ansible to automate AWS resource configuration based on tags and regions, enhancing scalability and flexibility in cloud infrastructure management.
- • Leveraged AWS API integration and Ansible’s ‘amazon.aws.aws_ec2’ plugin for real-time inventory updates, ensuring accurate and up-to-date resource targeting.
Project Lead
NCR Atleos · Mar 2023 – Dec 2025
- Directed a 12-engineer infrastructure engineering team to architect and scale NCR's core foundation-model infrastructure platform, supporting 120+ active ML engineers and provisioning low-latency compute capabilities for over 9,400+ enterprise accounts.
- Led a 12-engineer infrastructure team delivering a managed LoRA and DPO fine-tuning pipeline adopted by 1,200+ enterprise customers in its first two quarters, driving $34M in incremental ARR.
- Designed and deployed a 2,000 GPU large-scale training cluster utilizing dedicated InfiniBand interconnect networks, compressing the distributed training timeline of a 70B parameter model from 3+ weeks down to 4 days.
- Architected multi-tenant vLLM inference serving engines running speculative decoding and FP8 KV-cache quantization, lifting overall framework throughput 3.1x versus the legacy Triton stack.
- Slashed per-token inference serving costs by 62% through aggressive KV-cache optimization, smarter batching windows, and model weight quantization profiles.
- Built an autoscaling LLM inference serving platform handling 10M+ daily production requests with 99.95% high availability using Kubernetes orchestration and Triton Inference Server.
- Optimized production serving paths to deliver an ultra-low p95 latency benchmark of 340 ms while under a sustained load of 900 QPS distributed across 3 core operating regions.
- Engineered a high-throughput Python and FastAPI serving layer fronted by Azure Kubernetes Service (AKS), maintaining a strict p95 latency of 410 ms under peak traffic conditions.
- Recaptured $3.2M in annual cloud infrastructure spend by designing automated spot instance preemption handlers and stateful checkpoint optimizations across deep learning jobs.
- Developed custom cluster job scheduling algorithms that maximized hardware efficiency, successfully lifting baseline aggregate cluster utilization from 58% to 87%.
- Orchestrated multi-tenant Kubernetes infrastructure on AWS EKS to securely isolate resource limits, namespaces, and compute boundaries for 120+ active ML engineers.
- Implemented deep-stack NVIDIA GPU monitoring and quota management with Prometheus, Grafana, and Karpenter, expanding average GPU utilization across the org by 31%.
- Eliminated severe training data-starvation bottlenecks by building a zero-copy data pipeline utilizing NVIDIA DALI and targeted NFS v4 transport optimizations.
- Remediated data ingestion limits that were previously capping vision model GPU training utilization at a stalled 54%, unlocking peak hardware processing capacity.
- Standardized declarative infrastructure patterns via Terraform and Helm, cutting GPU environment provisioning times from 2 days to under 30 minutes with a 99.2% successful release rate across Python and Go automation workflows.
DevOps Engineer
NCR Corporation · Dec 2021 – Mar 2023
- Built GitHub Actions and Jenkins pipelines for Terraform, Ansible and serverless changes, establishing reusable delivery patterns transferable across cloud environments.
- Developed automated monitoring, alerting and remediation workflows with Terraform, Ansible, event-driven functions and Slack/email notification integrations.
- Automated dynamic resource configuration and application deployment through Ansible inventories, reducing reliance on manual environment changes.
- Supported production cloud-security incidents with policy-as-code, audit logging and automated response practices.
- Created reusable Infrastructure-as-Code modules and playbooks that reduced configuration drift by 35% and manual errors by 40% across environments.
DevOps Engineer
Ibexlabs · Nov 2021 – Dec 2021
- 1.
- Working on Ansible scripts to install Cloudwatch agent on EC2 instances.
- 2.
- Setting up multiple environment variables input on GitHub to deploy images to ECR.
I
DevOps Engineer
IbexLabs · Nov 2021 – Dec 2021
- Automated host monitoring and environment-specific container delivery with Ansible and parameterized GitHub workflows.
DevOps Engineer
twimbit · Sep 2021 – Oct 2021
- 1.
- Setup CloudFront along with Application Load Balancers for ECS
- 2.
- Setup Task definitions for a Caddy server and static website
- 3.
- Write Nginx configuration to reverse proxy traffic within the cluster and to serve SSL certificate on the go with the help of OpenResty Framework
- 4.
- Managing the entire infrastructure using terraform.
- Setup Lambda function for database failover and automate the process using step functions.
- 5.
- Setup A records and CNAME in Route 53.
Associate Consultant [Microsoft (AT&T Project)]
Neudesic · Mar 2021 – Aug 2021
- 1.
- Created a Windows server image using Hashicorp Packer
- 2.
- Deploys the Packer image on Azure Virtual Machine Scale Set using Terraform
- 3.
- Manages a GKE cluster using Terraform
- 4.
- Sets up Load Balancer for the Kubernetes cluster
DevOps Engineer
Neudesic · Mar 2021 – Aug 2021
- Standardized Windows Server provisioning with reusable Packer images and Terraform/Bicep-managed Azure VM Scale Sets, reducing configuration drift across environments.
- Resolved Azure provisioning and networking issues by codifying repeatable Infrastructure-as-Code fixes instead of manual environment repair.
- Recognized internally as a Terraform subject-matter expert for Microsoft collaboration based on reusable cloud-automation practices.
DevOps Intern
TivonaGlobal Technologies · Oct 2020 – Mar 2021
- 1.
- Continuous deployment automation using bash scripting.
- 2.
- Automated AWS cloud deployment using Terraform from scratch.
- 3.
- Implemented terraform functions on Terraform cloud.
- 4.
- Implemented sentinel policies on Terraform cloud.
- 5.
- Using dynamic blocks to dynamically create multiple resources of block within a resource from a complex value such
- as a list of map.
- 6.
- Create IAM policies for users.
- 7.
- Lambda function to attach the IAM policy to an IAM user and save the CloudTrail logs for IAM user in DynamoDB, using Boto.
T
DevOps Intern
Tivona Global · Oct 2020 – Feb 2021
- Automated continuous deployment with Bash and provisioned AWS infrastructure from scratch using Terraform, establishing a repeatable cloud-delivery foundation.
- Implemented Terraform Cloud Sentinel policies and dynamic Terraform blocks to enforce policy-as-code and create multiple resources from reusable complex values.
- Created IAM policies and group-based access controls; developed Boto3 Lambda automation to attach IAM policies and record CloudTrail activity in DynamoDB.
J
SWE Virtual Intern
JPMorgan Chase & Co. · May 2020 – May 2020
- 1.
- I was responsible for optimizing and troubleshooting a website.
- 2.
- I had to get familiar with JPMorgan Chase frameworks and tools.
- 3.
- Understanding the concepts of git was also part of the job.
- 4.
- Display data visually for traders (Trader's Dashboard)
- 5.
- Use JP Morgan's perspective framework.
Australia Discovery Program
Accenture · May 2020 – May 2020
- 1.Set Project Priorities
- 2.Assemble a plan
- 3.User Journey Redesign
- 4.Outcomes Analysis
- 5.Fix the errors
- 6.Prioritisation & Impact Assessment
Technical Consultant [Virtual Internship]
Deloitte · May 2020 – May 2020
- 1.Understanding Cloud Computing
- 2.Cloud Feasibility Assessment
- 3.Cloud Readiness Assessment
- 4.Client Discovery
- 5.Design a Business Case
- 6.Considerations For Mobilisation
- 7.Define the project approach
- 8.Conduct a market scan
- 9.Further analysis & solution presentation
Skills 0 proven through work
Also works with
Developer Feedback AnalysisExternal System State VerificationOperation Completion VerificationPost-Mortem AnalysisIterative Problem SolvingStrategic PlanningDivide and Conquer StrategyEnd-to-End Solution OwnershipAI Platform DevelopmentDeployment Verification AutomationApplication MigrationResource UtilizationApplication Performance OptimizationSoftware Quality AssuranceComparative Performance AnalysisProductivity AnalysisBusiness Value RealizationTool Adoption Change ManagementDependency ManagementCost EstimationIncident ManagementReliability ImprovementObservability Platform DevelopmentRetry Logic ImplementationGoal setting (defining key results)Workflow Design (Process Mapping)Data Repetition PreventionSolution ImplementationAWS IAM & Access ManagementAuthentication System IntegrationCode RefactoringGolden Path DevelopmentOperational Performance TrackingAutomated Workflow TestingMeeting FacilitationResource AllocationArchitectural DesignLLM Infrastructure DevelopmentBuild Agent UtilizationAccountability ManagementEmpowermentTechnical DiscussionTeamworkCritical ThinkingProject TrackingAdaptabilityAmbiguity ManagementInfrastructure ManagementMentoring and Peer CoachingIdea pitchingDistributed Systems DesignProduction-Grade System DesignML Detection Speed OptimizationIoT System DevelopmentAI Platform Architecture DesignSenior Engineering LeadershipTaking OwnershipSoftware Development PracticesKubernetes OrchestrationCloud ComputingStakeholder ManagementCybersecurity FundamentalsCloud Architecture AdvisoryOn-Device AI InferenceMachine Learning Model DeploymentStartup DevelopmentTechnical Issue DetectionDevOps ImplementationRegression TestingProduction Deployment VerificationIssue ReportingConcurrent Workflow ImplementationRelease ManagementBuild Cache ManagementAutomation Test DevelopmentCode CompilationPerformance Metrics AnalysisBefore-and-After Impact MeasurementIncremental DevelopmentUptime ManagementSecurity Posture ManagementRoot Cause AnalysisImpact AnalysisPerformance TestingServerless ArchitectureAnsibleJenkins Pipeline ConfigurationGitHub ActionsVercel DeploymentAWS DeploymentConnection Timeout ManagementLog AnalysisIdempotent Task DesignDistributed LockingTerraformArtifact ManagementTechnical TroubleshootingSoftware Architecture PrinciplesApplication Error LoggingTask AutomationUser ProvisioningEnterprise Integration DesignRBAC Module DevelopmentFault-Tolerant System DesignApache Airflow OrchestrationIdentity Provider IntegrationSecurity ArchitectureAttribute-Based Access ControlAPI Authentication ImplementationAPI IntegrationJira UsageStatic Code AnalysisSonarQube IntegrationVersion Control with GitHubServiceNow System AdministrationAsset ManagementSystem AdministrationSecurity ScanningInternal Developer Platform ArchitectureOperational Process MonitoringProcess ImprovementApplication MonitoringSecurity TestingApplication DeploymentIntegration TestingCode ReviewAgile MethodologyProject ExecutionRisk and Controls AssessmentProject Architecture PlanningTechnical Solution DesignWork Planning and PrioritizationRequirements AnalysisProblem SolvingDeveloper Experience ManagementPipeline SecurityCI/CD Pipeline ImplementationIaC Principles & PracticeTeam LeadershipScalable System Design
Proof of Work
Proof of Work
Pranay shares this with people who ask. You'll hear back either way.
Education
Bachelor of Technology, Electrical and Electronics Engineering
VIT University, Chennai · 2017 — 2021
Contact details
Contact details
Pranay shares this with people who ask. You'll hear back either way.
What drives their work
The Architect
Designs and builds the foundational systems that endure.
Pranay's superpower
You excel at architecting and implementing resilient, integrated infrastructure solutions across complex distributed systems.
How Pranay works
You are well-suited for roles that require both deep technical expertise in infrastructure and the ability to lead and mentor teams in building robust systems.
Ask about this candidate
AI responses may contain errors. Proof status and source information are provided by Proof of Skill.
A Proof CV — one profile, kept current, with the proof attached. Back to the portal