Senior Platform Engineer

Medi Assist; Bengaluru; On-site; INR 3,500,000 - 7,000,000; Full time

Job summary

Medi Assist is seeking a Senior Platform Engineer (AI/ML) to architect, build, and maintain next-generation cloud infrastructure and MLOps platforms. You will bridge core infra engineering with AI/ML data workflows to enable data science teams to train, serve, and monitor models at enterprise scale in Bengaluru.

You will design multi-tenant Kubernetes clusters, operate production model serving pipelines, deploy vector DBs for RAG workflows, orchestrate ETL/ELT pipelines, and drive GitOps and

Qualifications

• B.Tech / M.Tech / BCA / MCA in CS/IT or related field.
• Experience deploying and operating cloud infrastructure (AWS/GCP/Azure).
• Strong Kubernetes, Terraform, Docker and CI/CD expertise.
• Proven experience with ML platforms (KServe, Kubeflow, MLflow) and vector databases.
• Knowledge of data pipelines (Airflow, Kafka/Pub/Sub) and observability tools.

Responsibilities

• Design, provision, and maintain secure, multi-tenant Kubernetes clusters (EKS/GKE) using IaC (Terraform).
• Build production model serving pipelines using KServe/vLLM; manage model registries and experiments (MLflow/Kubeflow).
• Deploy vector databases ( Pinecone, pgvector, OpenSearch ) for high-throughput RAG workflows.
• Orchestrate ETL/ELT pipelines with Apache Airflow; support data/train/retrain workflows with Kafka or Pub/Sub.
• Drive GitOps and CI/CD with ArgoCD, FluxCD, GitHub Actions, Jenkins; enable zero-downtime deployments.
• Implement unified monitoring and drift detection with Prometheus, Grafana, Datadog.

Skills

Cloud foundations

Kubernetes

Terraform

ML platforms

Data pipelines

GitOps

CI/CD

Observability

Vector DBs

MLOps

Education

B.Tech / M.Tech / BCA / MCA in CS/IT

Tools

Terraform

Kubernetes

Docker

KServe

Kubeflow

MLflow

OpenSearch

Job description

We are looking for a Senior Platform Engineer (AI/ML) to architect, build, and maintain our next-generation cloud infrastructure and MLOps platforms. In this role, you will bridge the gap between core infrastructure engineering and AI/ML data workflows, enabling data science teams to seamlessly train, serve, and monitor machine learning and LLM models in production at enterprise scale.

Responsibilities:

• Internal Developer Platform (IDP): Design, provision, and maintain secure, multi-tenant Kubernetes clusters (EKS/GKE) using Infrastructure as Code (Terraform).
• AI/ML Model Serving and Lifecycle: Build and operate production model serving pipelines using vLLM, KServe, or AWS Bedrock; manage model registries and experiment tracking using MLflow or Kubeflow.
• Vector and GenAI Infrastructure: Deploy and optimise Vector Databases (pgvector, Pinecone, OpenSearch) to support high-throughput RAG (Retrieval-Augmented Generation) workflows.
• Data Pipeline Orchestration: Orchestrate scalable ETL/ELT pipelines and continuous model retraining workflows using Apache Airflow, PySpark, and event streams (Kafka/PubSub).
• GitOps and Automation: Drive zero-downtime microservice deployments across environments using GitOps tools (ArgoCD, FluxCD) and automated CI/CD pipelines (GitHub Actions, Jenkins).
• Observability and Drift Monitoring: Implement unified monitoring and alerting across platform infrastructure and AI models using Prometheus, Grafana, Datadog, and ML drift tools (Evidently AI).

The core requirements for the job include the following:

Must-Have Technical Expertise (The 4 Pillars):

• Cloud and Kubernetes Foundation: Hands‑on experience with AWS/GCP, Kubernetes (EKS or GKE), Docker, and modular Terraform infrastructure.
• AI / MLOps / LLM Platforms: Proven experience deploying ML models to production using KServe, vLLM, or AWS Bedrock; experience with Vector Databases (Pinecone/pgvector) and MLflow/Kubeflow.
• Data Pipelines: Hands‑on expertise with Apache Airflow DAGs, data movement pipelines, and event streaming (Kafka or GCP Pub/Sub).
• CI/CD and Observability: Strong proficiency in ArgoCD (GitOps), GitHub Actions/Jenkins, and observability tools (Prometheus, Grafana, Datadog, or OpenTelemetry).

Preferred Background:

• Experience in regulated, high-security data environments (HealthTech, InsurTech, FinTech, or high-throughput B2B SaaS).
• Hands‑on experience with secrets management (HashiCorp Vault, External Secrets Operator) and container security scanning tools (Trivy, Cosign).

Education and Certifications:

• B. Tech / M. Tech / BCA / MCA in Computer Science, Information Technology, or a related technical field.
• AWS Certified Solutions Architect or CKA (Certified Kubernetes Administrator) is a plus.