This role owns the software and cloud-native architecture of AI-enabled applications and retrieval systems, from design to production. It combines architectural leadership with hands-on engineering: designing GenAI and RAG solutions, building cloud-native backend services, and ensuring the security, reliability, and observability required for production workloads.

Requirements

What you will do

• Design scalable, secure, and resilient architectures for AI-enabled applications, defining service boundaries, data flows, APIs, and integration patterns.

• Define cloud-native patterns across microservices, containers, serverless, and event-driven systems.

• Design and productionize GenAI and RAG solutions: model selection and routing, retrieval strategy, evaluation, guardrails, and cost/latency optimization.

• Build backend services in TypeScript/Node.js and/or Python, and event-driven workflows with queues, workers, and webhooks.

• Define non-functional requirements, evaluate trade-offs, and document decisions in ADRs.

• Translate business use cases into technical designs, assessments, and executive summaries.

• Own the architecture from discovery to go-live, guiding engineers through architecture and code reviews.

• Implement observability and secure CI/CD pipelines.

Job requirements

• 7+ years of software engineering experience.

• Proven experience owning the architecture of production distributed systems (microservices, domain-driven design, REST and asynchronous APIs).

• Hands-on delivery of production GenAI or LLM applications, including evaluation and AI safety controls.

• Experience with RAG, embeddings, and vector databases (pgvector, OpenSearch, or equivalent).

• Strong TypeScript/Node.js or Python engineering experience.

• Deep knowledge of cloud-native patterns: containers and Kubernetes, serverless, event-driven messaging, and resilience patterns.

• Strong understanding of security in cloud-native systems: identity, authorization, secrets management, and data protection.

• Docker, CI/CD, automated testing, and observability (OpenTelemetry, Grafana, Datadog, or CloudWatch).

Nice to have

• AWS: Bedrock, Lambda, API Gateway, SQS, EventBridge, Step Functions, ECS/EKS, Aurora PostgreSQL, DynamoDB.

• Conversational and contact center: WhatsApp Business API, Amazon Connect, Amazon Lex, Twilio, voice bots.

• Terraform, CloudFormation, or CDK.

• AWS Certified Solutions Architect – Professional or equivalent.

• Customer-facing consulting experience and comfort presenting to executive stakeholders.

Engagement details

Part time

Remote

Contractor Hourly

Start: ASAP

Highlights

AWS (Bedrock, Lambda, SQS, EventBridge), GenAI / LLM, RAG & Vector Databases (pgvector, OpenSearch), TypeScript / Node.js, Python, Kubernetes, Docker, PostgreSQL, Terraform / CloudFormation / CDK

Originally posted on Himalayas