Junior AI/ML Engineer, GenAI, AWS

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

📋 Description

• Collaborate closely with an FDE and an FDX.

• Design and deploy production-grade GenAI systems within customer environments, incorporating cloud-native data, LLM-based, and agentic AI solutions.

• Develop and enhance RAG systems tailored for production scenarios.

• Create the evaluation harness prior to feature development.

• Write production-level code across AI, backend services, and data pipelines utilizing appropriate tools for each client.

• Integrate AI components seamlessly into backend services and RESTful APIs.

• Deploy systems to production on AWS, or GCP/Azure as per customer requirements.

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

• Start from initial blueprints, contributing to enablement and handover via documentation, runbooks, and collaboration with client engineers.

• Provide feedback on reusable components and insights to enhance Provectus Blueprints.

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

• Assess model performance, address identified failure modes, and optimize for efficiency and reliability.

• Mentor junior and mid-level AI engineers.

• Conduct code reviews and disseminate knowledge through documentation, presentations, and workshops.

⛳️ Requirements

• Proactive and self-motivated; seeks clarity rather than waiting for tasks to be assigned.

• Strong communication and problem-solving abilities.

• Comfortable navigating some uncertainty with guidance from senior team members.

• Proficient in English at a B2+ level, capable of collaborating across diverse, multicultural teams.

• Hands-on experience in building or contributing to RAG systems, preferably in production or near-production environments.

• Strong engineering foundation; proficiency in Python and/or TypeScript.

• Ability to quickly become productive in an unfamiliar codebase with some onboarding support.

• Practical experience with AWS services, such as Lambda, S3, ECS, or similar.

• Eager to advance into Bedrock and Bedrock AgentCore.

• Some familiarity with containers and CI/CD practices in real-world projects.

• Experience evaluating non-deterministic systems and participating in test/evaluation cycles.

• Basic understanding of model/agent monitoring concepts.

• Awareness of cost and latency trade-offs when working with LLMs.

• Hands-on experience with the Claude ecosystem is a plus, or a strong ability to learn quickly.

• Practical experience with LLM APIs such as Anthropic, AWS Bedrock, or OpenAI in real-world applications.

• A minimum of 2 years of software or ML engineering experience, including exposure to production systems.

• Solid foundations in AI/ML and comprehension of common model failure modes.

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

• Experience with spec-driven development is highly desirable.

• Understanding why an agent might prefer MCP over REST integration; experience authoring an MCP server is a plus.

• Experience in sectors such as financial services, insurance, or healthcare is advantageous.

• Experience in consulting, professional services, or customer-facing delivery roles is a plus.

• AWS and Claude Code certifications, or actively working towards them, are beneficial.

• Interest in agent-to-agent interoperability concepts is a plus.

• Experience with CI/CD pipelines using GitHub Actions or GitLab CI is desirable.

• Practical experience with NLP, LLMs, or recommendation engines is a plus.

• Familiarity with Go, TypeScript, or Rust is advantageous.

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

🏝️ Benefits

• A remote-friendly work culture.

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

• Opportunities to attend conferences.

• Career advancement and active engineering development.

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

• Long-term B2B collaboration opportunities.

• Private medical insurance or a budget for medical expenses.

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

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