FDE AI/Solutions Architect, AI, Python

This is a fully remote position, open to applicants in Ukraine, +6 more countries.

📋 Description

• Engage with the client and Forward Deployed Executive at the commencement of projects.

• Understand the client's operations from the ground up and reimagine them based on foundational principles.

• Attain proficiency in new fields such as insurance underwriting, healthcare revenue cycle, and asset flow.

• Design and deploy production GenAI systems within customer environments.

• Implement and enhance production RAG systems.

• Create evaluation frameworks, establish success metrics, instrument systems, and leverage evaluations to inform design decisions.

• Develop production code for AI, backend services, and data pipelines.

• Deploy systems to production on AWS or GCP/Azure when necessary, utilizing containers, CI/CD, automated testing, monitoring, and ensuring maintainability.

• Transition systems to clients and integrate field insights back into Provectus frameworks.

• Conduct architecture reviews, generate technical design documents, contribute to standards, mentor engineers, and disseminate knowledge.

• Collaborate with an FDX on Business Unit KPIs and take charge of the technical direction for proposals and scoping.

• Propel adoption and manage change effectively.

• Present results convincingly to customer engineers and executives.

• Shape commitments prior to finalization.

⛳️ Requirements

• B2+ English proficiency, comfortable working with distributed, multicultural teams.

• Proactive and self-motivated; able to identify issues before they are assigned.

• Comfortable with uncertainty and capable of taking ownership.

• Willing to invest time in understanding and performing tasks on the client's side before starting coding.

• Credibility with senior stakeholders, including Business Unit leaders and CTOs.

• Ability to create scoped, phased delivery plans that outline deliverables, dependencies, risks, and cost estimates.

• Over 7 years of experience in building and managing production systems.

• Robust foundations in AI/ML and the ability to analyze model failure modes.

• Experience in designing and launching production LLM applications and agentic workflows.

• Proficient in multi-step workflows, graph-based orchestration, tool utilization, state management, and recovery from partial failures.

• Familiarity with LLM APIs such as Anthropic, AWS Bedrock, or OpenAI, along with agent frameworks.

• Experience in constructing and optimizing RAG systems in production.

• Strong engineering fundamentals with proficiency in Python and/or TypeScript.

• Experience in making and justifying architectural trade-off decisions.

• Hands-on production experience with AWS technologies, including Bedrock, Bedrock AgentCore, Lambda, ECS, S3, SQS, ECR, or similar services.

• Cloud-native delivery experience using containers, ECS or Kubernetes, Infrastructure as Code (IaC), and CI/CD applied to AI pipelines.

• Experience in building or managing an evaluation suite for a non-deterministic system.

• Familiarity with model and agent monitoring and drift detection.

• Discipline in cost and latency management, including model tiering and caching.

• Hands-on production experience with the Claude ecosystem, including Claude Code, CLAUDE.md, hooks, and skills files.

• Ability to articulate why an agent might prefer MCP over a REST integration.

• Nice to have: experience as a founder, CTO, or in an engineering leadership role.

• Nice to have: experience in financial services, insurance, or healthcare sectors.

• Nice to have: background in consulting, professional services, or customer-facing delivery roles.

• Nice to have: knowledge of A2A interoperability.

• Nice to have: certifications in AWS and Claude Code.

• Nice to have: experience with CI/CD pipelines using GitHub Actions or GitLab CI.

• Nice to have: skills in Go, TypeScript, or Rust.

• Nice to have: experience with Apache Spark, Apache Airflow, or Kafka.

🏝️ Benefits

• A culture that embraces remote work.

• Comprehensive internal training programs with full support for Claude, AWS, and other professional certifications.

• Opportunities to attend conferences.

• Career advancement; we are committed to developing our engineers.

• Access to the latest AI tools and premium subscriptions.

• Long-term B2B collaboration opportunities.

• Private medical insurance or a budget for your healthcare needs.

• Paid sick leave, vacation, and public holidays.

• Provision of equipment and technology necessary for comfortable and productive work.