AWS DevSecOps & LLMOps Engineer

We are seeking a skilled and hands-on DevSecOps & LLMOps Engineer with strong expertise in AWS Cloud, DevSecOps, API Engineering, and enterprise Generative AI platforms. The ideal candidate will design, build, secure, and operate scalable cloud infrastructure and AI applications while driving automation, observability, production operations, and modern LLMOps practices using AWS Bedrock and related technologies.

Your core responsibilities include

· Design, implement, and support secure, scalable AWS infrastructure and AI platforms using Terraform, GitHub Actions, Ansible, ECS/Fargate, and AWS native services.

· Build and operationalize enterprise GenAI solutions using Amazon Bedrock, LLMs, RAG pipelines, vector databases, embeddings, chunking strategies, workflow orchestration (DAG/agentic), and AI observability.

· Develop and maintain CI/CD pipelines, Infrastructure as Code, API integrations, cloud security, IAM governance, monitoring, logging, and production BAU support.

· Configure and manage application observability using Datadog (or equivalent), including dashboards, APM, log analytics, infrastructure monitoring, alerting, and operational health reporting.

· Collaborate with architects, developers, security teams, and business stakeholders to deliver secure, resilient, scalable, and cost-effective cloud and AI solutions.

Required Skills

· Bachelor's degree in computer science, Engineering, or equivalent experience.

· Strong hands-on experience with AWS services including Amazon Bedrock, ECS/Fargate, Lambda, EC2, API Gateway, VPC, ALB, IAM, CloudWatch, S3, EFS, DynamoDB, Neptune, and Infrastructure as Code using Terraform.

· Strong experience with DevSecOps practices including GitHub Actions, Ansible, Docker, CI/CD automation, security scanning, secrets management, monitoring, logging, and production support.

· Good understanding of LLMOps concepts including LLMs, RAG, embeddings, chunking, vectorization, vector databases, semantic search, prompt engineering, workflow orchestration (DAG/LangGraph), AI guardrails, and model evaluation.

· Strong experience with API Management platforms such as Amazon API Gateway, Kong, Apigee, or equivalent, with the ability to design, configure, and implement API proxy workflows, authentication, routing, policies, transformations, and API integrations.

· Strong experience with Datadog (or equivalent monitoring platform) for dashboard creation, application monitoring, alert configuration, APM, log analytics, and performance troubleshooting.

· Excellent communication, stakeholder management, and client-facing skills.

Good to Have

· Experience with Kubernetes/EKS, Docker, ServiceNow, Jira, GitHub Runners, CloudFormation, Route 53, WAF, EventBridge, Step Functions, and serverless architectures.

· Hands-on experience with Python development for automation, API integrations, scripting, and cloud-native application development.

· Experience building AI data pipelines, including document ingestion, preprocessing, metadata enrichment, chunking, embedding generation, vector indexing, and retrieval workflows.

· Familiarity with AI prompt development, prompt tuning, prompt templates, and prompt evaluation techniques.

· Exposure to vector databases, OpenSearch, LangChain/LangGraph, knowledge graphs (Neptune), cloud networking, security best practices, cost optimization, and enterprise production support.