Senior AI/ML Engineer (GenAI, AWS)

About the role

Provectus is seeking a Senior AI/ML Engineer to design and deliver production‑grade generative AI solutions for enterprise clients. You will join a senior pod that collaborates closely with Forward Deployed Executives and Engineers to turn business problems into agentic systems that run reliably at scale.

Key responsibilities

• Partner with Forward Deployed Executives to understand client KPIs and translate them into technical specifications.
• Architect, build, and ship agentic workflows that integrate large language models, tool use, state management, and recovery from partial failures.
• Own the technical direction of components, ensuring evaluation, observability, and guardrails are in place.
• Maintain production‑ready codebases, optimize RAG pipelines, and support ongoing client adoption.
• Collaborate with cross‑functional teams across AI, backend, and cloud infrastructure to deliver end‑to‑end solutions.

Required profile

• Proactive, self‑directed mindset with strong communication and problem‑solving skills.
• Comfortable working in ambiguous, multicultural environments and fluent in English (B2+).
• 5+ years of software or ML engineering experience with responsibility for production systems.
• Solid AI/ML foundations and ability to reason about model failure modes.
• Track record of shipping production LLM applications and agentic workflows, not just demos or notebooks.

Required skills

• Python and/or TypeScript programming.
• Hands‑on experience with AWS services: Bedrock, Lambda, ECS, S3, SQS, ECR.
• Familiarity with GCP or Azure environments.
• Experience using LLM APIs (Anthropic, AWS Bedrock, OpenAI) and agent frameworks.
• Building and optimizing Retrieval‑Augmented Generation (RAG) systems in production.
• Agentic orchestration: multi‑step workflows, graph‑based orchestration, tool integration, state management, and failure recovery.