Senior ML Engineer (LLMs, AWS)

Stack

Responsibilities

• ▹Work in a pair with a Forward Deployed Engineer (FDE) and a Forward Deployed Executive (FDX)
• ▹Build and ship production GenAI systems into the customer's environment (cloud-native data, LLM-based and agentic AI solutions)
• ▹Build and optimize RAG systems for production use cases
• ▹Build the evaluation harness before you build the feature
• ▹Write production code across the stack: AI, backend services, data pipelines
• ▹Integrate AI components into backend services and RESTful APIs
• ▹Take systems to production on AWS (GCP or Azure where the customer requires it): containerised, with CI/CD
• ▹Implement LLMOps and AgentOps practices: agent tracing, prompt and version management, cost and latency monitoring, regression testing, drift detection
• ▹Contribute to enablement and handover: documentation, runbooks and pairing with the client engineers who inherit the system
• ▹Feed reusable components and lessons back into the Provectus Blueprints
• ▹Participate in technical discussions and architectural decisions
• ▹Conduct model evaluation, improve failure modes and optimize model performance, efficiency and reliability
• ▹Mentor junior and mid-level AI engineers, conduct code reviews and share knowledge

Requirements

• ▹5+ years in software or ML engineering, with production systems you were accountable for
• ▹Solid AI/ML foundations: understand what models do well enough to reason about failure modes
• ▹Shipped LLM applications and agentic workflows to production, not demos, POCs or notebooks
• ▹Agentic orchestration: multi-step workflows, graph-based orchestration, tool use, state management and recovery from partial failure
• ▹Experience with LLM APIs (Anthropic, AWS Bedrock or OpenAI) and agent frameworks
• ▹Experience building and optimizing RAG systems in production
• ▹Strong engineering fundamentals and a full-stack mindset across AI, backend development and cloud infrastructure
• ▹Python and/or TypeScript proficiency; depth matters more than stack
• ▹Hands-on AWS in production: Bedrock, Bedrock AgentCore, Lambda, ECS, S3, SQS, ECR or similar
• ▹Cloud-native delivery: containers, ECS or Kubernetes, IaC and CI/CD applied to AI pipelines
• ▹Built or owned an eval suite for a non-deterministic system and can explain what was measured, how ground truth was produced and what gated a release
• ▹Model and agent monitoring, drift detection
• ▹Cost and latency discipline: model tiering, caching, estimating workload cost before it runs
• ▹Hands-on production experience with the Claude ecosystem: Claude Code, CLAUDE.md, hooks, skills files
• ▹MCP: can explain why an agent would prefer it to a REST integration
• ▹B2+ English, comfortable collaborating across distributed, multicultural teams

Nice to have

• ▹Spec-driven development: writing intent, constraints and acceptance criteria before letting an agent build (strong plus)
• ▹Having authored an MCP server
• ▹Experience in financial services, insurance or healthcare
• ▹Consulting, professional services or other embedded customer-facing delivery
• ▹AWS and Claude Code certifications
• ▹A2A: can explain agent-to-agent interoperability
• ▹CI/CD pipeline experience (GitHub Actions, GitLab CI)
• ▹Practical experience with NLP, LLMs and recommendation engines
• ▹Experience in an additional language (Go, TypeScript or Rust)
• ▹Experience with Apache Spark, Apache Airflow and Kafka
• ▹GCP or Azure experience

Soft skills

What we offer

• ▹The chance to shape how leading enterprises across LATAM, Europe and North America adopt AI
• ▹A forward-deployed model working in small, senior teams alongside an FDE and an FDX
• ▹A growing AI delivery practice where you help build the tooling and frameworks
• ▹Remote-friendly culture
• ▹Internal training programs with full support for Claude, AWS and other certifications, and conference attendance
• ▹Career growth
• ▹Access to the latest AI tools and premium subscriptions
• ▹Long-term B2B collaboration
• ▹Private medical insurance or a budget for medical needs
• ▹Paid sick leave, vacation and public holidays
• ▹Equipment and tech for comfortable, productive work

About the company

Provectus is an AWS Premier Partner and an Anthropic Strategic Partner working at the frontier of applied AI. It helps enterprises turn Claude, agentic systems and their own data into measurable business outcomes. With offices in North America, LATAM and EMEA, it focuses on financial services and insurance and on healthcare and life sciences.