Senior AI/ML Engineer (GenAI, AWS)

About the role

Provectus, an AWS Premier Partner and Anthropic Strategic Partner, works with enterprises to turn Claude, agentic systems and their own data into business outcomes, mainly in Financial Services & Insurance and Healthcare & Life Sciences. This Senior AI/ML Engineer role sits in a small senior pod with a Forward Deployed Engineer (FDE) and a Forward Deployed Executive (FDX), working alongside client leadership to deliver production GenAI systems.

Key responsibilities

• Build and ship production GenAI systems (cloud-native, LLM-based and agentic) into the customer's environment
• Build and optimise RAG systems for production use cases
• Build the evaluation harness before the feature, then write production code across the stack (AI, backend services, data pipelines)
• Integrate AI components into backend services and RESTful APIs
• Deploy on AWS (GCP or Azure where required): containerised, CI/CD, with LLMOps and AgentOps practices including agent tracing, prompt and version management, drift detection and cost/latency monitoring
• Contribute to enablement and handover: documentation, runbooks and pairing with client engineers, and feed reusable components back into the Blueprints
• Take part in architecture decisions, mentor junior and mid-level engineers, review code and share knowledge

Required profile

• 5+ years in software or ML engineering with production systems you were accountable for
• Shipped LLM applications and agentic workflows to production, not demos or notebooks
• B2+ English, proactive, self-directed and comfortable with ambiguity
• Nice to have: experience in financial services, insurance or healthcare; consulting or embedded customer-facing delivery; AWS and Claude Code certifications; CI/CD pipeline experience; Go, TypeScript or Rust; Apache Spark, Airflow or Kafka

Required skills

• LLM APIs (Anthropic, AWS Bedrock or OpenAI) and agent frameworks
• Production RAG systems and agentic orchestration (multi-step workflows, graph-based orchestration, tool use, state management)
• Python and/or TypeScript; hands-on AWS (Bedrock, Bedrock AgentCore, Lambda, ECS, S3, SQS, ECR)
• Containers, ECS or Kubernetes, IaC and CI/CD for AI pipelines
• Evaluation suites, model monitoring and drift detection; cost and latency discipline
• Hands-on experience with the Claude ecosystem (Claude Code, CLAUDE.md, hooks, skills files)

What we offer

• Remote-friendly culture and internal training with support for certifications and conferences
• Career growth, access to the latest AI tools and premium subscriptions
• Private medical insurance or a medical budget, paid sick leave, vacation and public holidays
• Equipment and all the tech needed for the job

Hiring involves an introductory conversation, a technical interview with live engineering sessions, and an HR interview.