Harshita Agarwal

DevOps Engineer

Bhopal, Madhya Pradesh, India4 yrs 9 mos experience

Key Highlights

4+ years of experience in DevOps and SRE.
Expertise in cloud platforms: GCP, AWS, Azure.
Proven track record in CI/CD automation and observability.

Stackforce AI infers this person is a DevOps and Site Reliability Engineer with a focus on AI and cloud infrastructure.

Contact

Skills

Core Skills

DevopsCloud InfrastructureSite Reliability Engineering

Other Skills

AWSAlgorithmsAmazon EKSAmazon Web Services (AWS)AnsibleAzureAzure DevOps ServicesBashBootstrapBotoCI/CDCascading Style Sheets (CSS)Cloud ComputingContainerizationContinuous Integration (CI)

About

I'm a DevOps/Site Reliability Engineer with 4+ years of experience across GCP, AWS, and Azure environments—deploying scalable infrastructure, automating CI/CD pipelines, and leading observability migrations. I currently work in the emerging space of LLM evaluation, where I bring my technical domain expertise to refine and assess AI-generated content related to DevOps, cloud, scripting, and system design. I evaluate LLM responses across quality, truthfulness, and grounding rubrics—contributing to better AI agents for developers. 🔧 Key Skills: Kubernetes, Terraform, Prometheus, Python, Bash, GitHub Actions, SRE practices, infrastructure as code 🤖 AI Roles: LLM trainer, prompt evaluator, rubric-based RLHF tasks, DevOps Copilot evaluations 📍 Open to: Remote DevOps/AI Infrastructure roles | Contract or Full-Time | Evaluation & Automation

Experience

4 yrs 9 mos

Total Experience

11 mos

Average Tenure

11 mos

Current Experience

Turing

LLM Trainer - DevOps | Amazon IAC RLHF Project

Jul 2025 – Present · 11 mos · United States · Remote

Evaluated AI-generated responses on DevOps, cloud infrastructure, and Python automation topics using rubric-based frameworks (Soul AI, Claude, OpenAI-style evals).
Provided ranking, rewriting, and scoring for tasks involving CI/CD, Terraform, Kubernetes, network design, and monitoring.
Worked on model-breaking prompt analysis, enabling fine-tuning and RLHF pipelines for DevOps assistant agents.

DevOpsCloud InfrastructurePythonCI/CDKubernetesTerraform

Neuron7.ai

MTS-DevOps (L4)

Oct 2024 – Jan 2025 · 3 mos · Remote

Worked with Azure infrastructure for secure deployments and audit compliance using Wiz and Terraform.
Implemented CI/CD workflows, containerized microservices, and set up monitoring for production pipelines.
Collaborated with ML teams to deploy inference pipelines and tune infrastructure for AI workloads.

AzureTerraformCI/CDContainerizationMonitoringCloud Infrastructure+1

Joveo

Site Reliability Engineer (L3)

Oct 2023 – Oct 2024 · 1 yr · Remote

Deployed and managed observability stack using Prometheus, Grafana, and Loki (self-hosted).
Led migration from Datadog to OSS monitoring stack including alerts, metrics, and dashboards.
Ensured 99.99% uptime across production environments hosted on AWS; used Terraform and Helm for infrastructure provisioning.

PrometheusGrafanaTerraformAWSMonitoringSite Reliability Engineering+1