FDE AI/Solutions Architect (AI, Python/Data)

Stack

Responsibilities

• ▹Design and ship production GenAI systems (cloud-native data, LLM-based, agentic AI)
• ▹Implement and optimize RAG systems for production use cases
• ▹Build the evaluation harness before building the feature
• ▹Write production code across the stack - AI, backend, data pipelines
• ▹Take systems to production on AWS (GCP/Azure where required): containerized, CI/CD, automated testing, monitoring
• ▹Hand systems over to the client, documented and maintainable
• ▹Lead architecture reviews, produce technical design documents
• ▹Mentor engineers and share knowledge across the team
• ▹Own technical direction of proposals and scoping

Requirements

• ▹7+ years building and running production systems
• ▹Solid AI/ML foundations, understanding of model failure modes
• ▹Designed and shipped production LLM applications and agentic workflows (not demos)
• ▹Agentic orchestration: multi-step workflows, graph-based orchestration, tool use, state management
• ▹Experience with LLM APIs (Anthropic, AWS Bedrock, OpenAI) and agent frameworks
• ▹Experience building and optimizing production RAG systems
• ▹Strong engineering fundamentals, productive in unfamiliar codebases
• ▹Python and/or TypeScript proficiency
• ▹Experience making and defending architectural trade-off decisions
• ▹Hands-on AWS production depth: Bedrock, Bedrock AgentCore, Lambda, ECS, S3, SQS, ECR
• ▹Cloud-native delivery: containers, ECS or Kubernetes, IaC, CI/CD for AI pipelines
• ▹Built or owned an eval suite for a non-deterministic system
• ▹B2+ English

Nice to have

• ▹GCP or Azure experience

Soft skills

About the company

Provectus is a solutions delivery company that pairs Forward Deployed Executives and Engineers to build production-grade GenAI and data systems inside client environments.