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

Stack

Responsibilities

• ▹Sit with the client and the Forward Deployed Executive at the start of an engagement, learn the function from the inside and redesign it from first principles; reach working fluency in a new domain (insurance underwriting, healthcare revenue cycle, asset flow)
• ▹Design and ship production GenAI systems into the customer's environment (cloud-native data, LLM-based and agentic AI solutions)
• ▹Implement and optimize RAG systems for production use cases
• ▹Build the evaluation harness before you build the feature: define what working means, instrument it and let the evals drive the design
• ▹Write production code across the stack (AI, backend services, data pipelines); tools are chosen to fit the customer
• ▹Take systems to production on AWS (GCP or Azure where the customer requires it): containerised, CI/CD, automated testing, monitoring and maintainable after the team leaves
• ▹Hand the system over to the client; start from the blueprint and feed the blueprint, so what you learn in the field becomes the baseline for the next engagement
• ▹Lead architecture reviews, produce technical design documents and contribute to standards
• ▹Mentor engineers and share knowledge across the team
• ▹Own the outcome: work in a pair with an FDX who carries the Business Unit's KPIs, and be measured against the same number
• ▹Own the technical direction of technical proposals and scoping
• ▹Drive adoption: change management is part of the engineering job; be credible with the customer's engineers and their executives
• ▹Shape what the company commits to before it commits

Requirements

• ▹Proactive and self-directed; identify problems before they're handed to you
• ▹Comfort with ambiguity and ownership: engagements start underspecified by design and closing that gap is the job
• ▹B2+ English, comfortable collaborating across distributed, multicultural teams
• ▹Willingness to spend time understanding and doing someone else's job on the client's side before you write a line of code
• ▹Credible with senior stakeholders: able to hold a redesign conversation with a BU head and a scoping conversation with a CTO, presenting outcomes to them
• ▹Able to produce a scoped, phased delivery plan with clear deliverables, dependencies and risks, and estimate what it will cost to build and to run
• ▹7+ years building and running production systems
• ▹Solid AI/ML foundations: understand what the models do well enough to reason about failure modes
• ▹Designed and shipped to production LLM applications and agentic workflows (not demos, POCs or notebooks)
• ▹Agentic orchestration: multi-step workflows, graph-based orchestration, tool use, state management and recovery from partial failure
• ▹Experience with LLM APIs (Anthropic, AWS Bedrock or OpenAI) and agent frameworks
• ▹Experience building and optimizing RAG systems in production
• ▹Strong engineering fundamentals: productive when dropped into an unfamiliar codebase or language
• ▹Python and/or TypeScript proficiency; depth matters more than stack
• ▹Experience in making and defending architectural trade-off decisions
• ▹Hands-on AWS production depth: Bedrock, Bedrock AgentCore, Lambda, ECS, S3, SQS, ECR or similar (GCP or Azure is a plus)
• ▹Cloud-native delivery: containers, ECS or Kubernetes, IaC and CI/CD applied to AI pipelines
• ▹Evaluation: have built or owned an eval suite for a non-deterministic system and can explain what you measured, how you produced ground truth and what gated a release
• ▹Model and agent monitoring, drift detection
• ▹Cost and latency discipline: model tiering, caching and the ability to say what a workload costs to run before it runs
• ▹Hands-on production experience with the Claude ecosystem: Claude Code, CLAUDE.md, hooks, skills files
• ▹MCP: can say why an agent would prefer it to a REST integration (having authored a server is a plus)

Nice to have

• ▹Prior experience as a founder, CTO or engineering leader who has chosen to return to individual contribution
• ▹Experience in financial services, insurance or healthcare
• ▹Consulting, professional services or other embedded customer-facing delivery experience
• ▹A2A: can explain agent-to-agent interoperability
• ▹AWS and Claude Code certifications
• ▹CI/CD pipeline experience (GitHub Actions, GitLab CI)
• ▹Experience in an additional language (Go, TypeScript or Rust)
• ▹Experience with Apache Spark, Apache Airflow and Kafka
• ▹Spec-driven development (writing the intent, constraints and acceptance criteria before you let an agent build) is a strong plus

Soft skills

What we offer

• ▹The chance to shape how leading enterprises across LATAM, Europe and North America adopt AI, from strategy through first deployment
• ▹A forward-deployed model working in small, senior teams alongside Principal Architects and Forward Deployed Engineers
• ▹A growing AI delivery practice where you help build the tooling and frameworks, not just use them
• ▹Remote-friendly culture
• ▹Internal training programs with full support for Claude, AWS and other professional certifications, and conference attendance
• ▹Career growth; the company actively develops its engineers
• ▹Access to the latest AI tools and premium subscriptions
• ▹Long-term B2B collaboration
• ▹Private medical insurance or a budget for medical needs
• ▹Paid sick leave, vacation and public holidays
• ▹Equipment and all the tech you need

About the company

Provectus is an AWS Premier Partner and an Anthropic Strategic Partner that helps enterprises turn Claude, agentic systems and their own data into measurable business outcomes. It focuses on Financial Services & Insurance and Healthcare & Life Sciences, with offices in North America, LATAM and EMEA.