Junior AI/ML Engineer – Generative AI & AWS

About the role

Provectus is seeking a Junior AI/ML Engineer to join a senior pod focused on generative AI solutions built on AWS and Anthropic technologies. You will collaborate with senior AI engineers and developers to deliver production‑grade Retrieval‑Augmented Generation (RAG) systems and agentic applications for clients in financial services, insurance, healthcare, and life sciences.

Key responsibilities

• Contribute to the design, development, and deployment of RAG pipelines and AI Blueprints.
• Write and maintain production‑ready code in Python and/or TypeScript.
• Integrate LLM APIs (Anthropic, AWS Bedrock, OpenAI) and Claude ecosystem components.
• Support CI/CD pipelines, containerised workloads (Docker/ECS) and AWS services such as Lambda, S3, and ECS.
• Assist in testing, evaluation, and monitoring of non‑deterministic AI models.
• Collaborate with distributed, multicultural teams and communicate progress in English.

Required profile

• Proactive, self‑directed mindset with strong problem‑solving abilities.
• Comfortable working with some ambiguity and seeking clarification.
• 2+ years of software or ML engineering experience, including exposure to production systems.
• Solid understanding of AI/ML fundamentals and common model failure modes.
• Fluent B2+ English and able to work in a distributed team.

Required skills

• Python programming.
• TypeScript (optional but preferred).
• AWS services: Lambda, S3, ECS, Bedrock.
• Containerisation (Docker) and CI/CD tools (GitHub Actions, GitLab CI).
• Experience with Retrieval‑Augmented Generation (RAG) systems.
• Working with LLM APIs (Anthropic, OpenAI, AWS Bedrock).
• Familiarity with Claude Code, CLAUDE.md, hooks, and skills files.
• Basic knowledge of model/agent monitoring and evaluation cycles.