Senior AI/ML Engineer, GenAI, AWS

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

📋 Description

• Collaborate with an FDE and an FDX in a paired work environment.

• Develop and deploy production GenAI systems within customer settings.

• Design and enhance RAG systems for real-world applications.

• Create the evaluation harness prior to feature development.

• Write production-grade code across artificial intelligence, backend services, and data pipelines.

• Integrate AI components into backend services and RESTful APIs.

• Deploy systems to AWS, or GCP/Azure as required by customer needs.

• Implement LLMOps and AgentOps methodologies, including agent tracing, prompt and version management, cost and latency monitoring, regression testing, and drift detection.

• Assist in enablement and handover through documentation, runbooks, and collaboration with client engineers.

• Contribute reusable components and insights back into Provectus Blueprints.

• Engage in technical discussions and participate in architectural decision-making.

• Conduct model evaluations, enhance failure modes, and optimize model performance, efficiency, and reliability.

• Mentor junior and mid-level AI engineers, carry out code reviews, and disseminate knowledge through documentation, presentations, and workshops.

⛳️ Requirements

• Proactive and self-motivated; you seek clarity rather than waiting for tasks.

• Strong communication and problem-solving abilities.

• Comfortable navigating ambiguity and taking ownership.

• B2+ English proficiency, with the ability to collaborate across distributed, multicultural teams.

• Over 5 years of experience in software or ML engineering, with accountability for production systems.

• Solid foundations in AI/ML and the capacity to analyze model failure modes.

• Experience shipping production LLM applications and agentic workflows — not just demos, POCs, or notebooks.

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

• Experience with LLM APIs such as Anthropic, AWS Bedrock, or OpenAI, as well as agent frameworks.

• Proven experience building and optimizing RAG systems in production environments.

• Proficiency in Python and/or TypeScript.

• Full-stack experience encompassing AI, backend development, and cloud infrastructure.

• Practical experience with AWS in production, including Bedrock, Bedrock AgentCore, Lambda, ECS, S3, SQS, ECR, or similar services.

• Experience in cloud-native delivery using containers, ECS or Kubernetes, IaC, and CI/CD applied to AI pipelines.

• Developed or overseen an evaluation suite for a non-deterministic system.

• Experience with model and agent monitoring, as well as drift detection.

• Expertise in cost and latency optimization strategies, including model tiering and caching.

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

• Understanding of MCP and the reasons an agent might prefer it over REST integration.

• Experience with an additional programming language such as Go, TypeScript, or Rust is advantageous.

• Familiarity with Apache Spark, Apache Airflow, or Kafka is a plus.

🏝️ Benefits

• Remote-friendly work culture.

• Internal training programs with comprehensive support for Claude, AWS, and other professional certifications.

• Opportunities for conference attendance.

• Career advancement opportunities; we actively invest in our engineers' development.

• Access to cutting-edge AI tools and premium subscriptions.

• Long-term B2B collaboration.

• Private medical insurance or a budget for personal medical needs.

• Paid sick leave, vacation days, and public holidays.

• Provision of equipment and all necessary technology for effective and productive work.