[VCK] Senior DevOps Engineer AWS / AI Infrastructure

Job Description

About the Project 

Software Mind is building a private, tenant-isolated AI assistant for the real estate title and settlement industry. The platform is a retrieval-first (RAG) system that ingests historical email, documents, and structured metadata into a per-tenant vector index, and serves grounded, cited, expert-weighted answers through a chat-style Q&A interface with single sign-on and full audit logging. 

The platform is AWS-native with a Python/FastAPI backend, Vue.js frontend, OpenSearch/Pinecone vector store, and OpenAI/Anthropic/Bedrock as LLM provider. You will join a senior, cross-functional LATAM-based team where hands-on AI delivery experience not just familiarity is the baseline expectation. 

You stand up and own the cloud infrastructure and CI/CD foundation the entire project runs on. Your work is on the critical path from day one: delivery begins with environment provisioning. You design for tenant isolation, observability, and security from the outset not as an afterthought. This role requires prior experience operating infrastructure for production AI or LLM-based workloads. 

 

Your Responsibilities 

• Provision and configure a dedicated VPC and segmented cloud environment on AWS 

• Build the baseline CI/CD pipeline and maintain and evolve it across all delivery phases 

• Configure and manage the vector store infrastructure (OpenSearch/Pinecone on AWS) 

• Set up and manage the observability stack: CloudWatch, X-Ray, alerting thresholds, and LLM-specific monitoring 

• Implement infrastructure-as-code for all environments (dev, staging, production) using Terraform or CDK 

• Manage secrets, KMS encryption key configuration, and tenant-scoped access controls 

• Configure LLM provider connectivity (OpenAI / Anthropic / Amazon Bedrock enterprise tier, zero-data-retention) 

• Define and implement environment promotion strategy aligned with the 2-week sprint cadence 

• Support incremental ingestion pipeline infrastructure requirements and nightly scheduling 

 

Qualifications

Must-Have Skills & Experience 

• 6+ years in DevOps or cloud infrastructure engineering; strong AWS specialisation required 

• Infrastructure-as-code: Terraform, CloudFormation, or AWS CDK 

• CI/CD tooling: GitHub Actions, AWS CodePipeline, or equivalent 

• Core AWS services: VPC, ECS, Lambda, S3, DynamoDB, API Gateway, Cognito, CloudWatch, X-Ray 

• Experience designing and operating multi-tenant cloud environments with tenant-level data isolation 

 

AI Experience (Required Not Optional) 

• At least one project operating infrastructure for a production AI/ML or LLM-integrated system not just general cloud workloads 

• Experience configuring and managing vector store infrastructure (OpenSearch, Pinecone, Weaviate, or equivalent) in a production environment 

• Familiarity with LLM provider APIs (OpenAI, Anthropic, or Amazon Bedrock) in a production/enterprise configuration, including zero-data-retention tier setup 

• Understanding of AI-specific observability concerns: token usage monitoring, latency profiling for LLM calls, and model response logging 

Additional Information