6 months ago
Valencia, SpainSenior
Responsibilities
- Embed with clients to understand workflows, identify underlying business problems, and redesign functions from first principles.
- Design, build, optimize, and deploy production GenAI, LLM-based, agentic, backend, and data pipeline systems.
- Implement production RAG systems and build evaluation harnesses with defined success criteria, ground truth, and release gates.
- Develop multi-step agent workflows with orchestration, tool use, state management, and recovery from partial failure.
- Deploy maintainable systems on AWS or other required cloud platforms using containers, CI/CD, automated testing, monitoring, and operational handoff.
- Lead architecture reviews, write technical design documents, contribute to engineering standards, and mentor engineers.
- Own technical direction for proposals and scoping, including delivery plans, dependencies, risks, build costs, and run costs.
- Present outcomes to senior client stakeholders, support adoption and change management, and feed field learnings back into reusable blueprints.
Requirements
- 7+ years of experience building and running production systems.
- Strong AI/ML foundations and the ability to reason about model failure modes.
- Experience designing and shipping production LLM applications and agentic workflows, not only demos, proofs of concept, or notebooks.
- Experience with LLM APIs such as Anthropic, AWS Bedrock, or OpenAI and with agent frameworks.
- Production experience building and optimizing RAG systems, evaluation suites, model and agent monitoring, and drift detection.
- Python and/or TypeScript proficiency, strong engineering fundamentals, and the ability to work productively in unfamiliar codebases or languages.
- Hands-on AWS production experience with services such as Bedrock, Bedrock AgentCore, Lambda, ECS, S3, SQS, and ECR; GCP or Azure experience is a plus.
- Experience with containers, ECS or Kubernetes, infrastructure as code, and CI/CD for AI pipelines.
- Experience with production Claude ecosystem tools including Claude Code, CLAUDE.md, hooks, and skills files.
- Knowledge of MCP and the ability to explain its advantages over REST integrations; authoring an MCP server is a plus.
- Ability to make and defend architectural trade-offs, control model cost and latency, and work with model tiering and caching.
- B2+ English proficiency and comfort collaborating across distributed, multicultural teams.
- Ability to engage credibly with business leaders, CTOs, engineers, and other senior stakeholders.
- Preferred qualifications include founder, CTO, or engineering leadership experience; financial services, insurance, or healthcare experience; consulting or embedded delivery experience; A2A knowledge; AWS or Claude Code certifications; GitHub Actions or GitLab CI experience; Go, TypeScript, or Rust experience; and Apache Spark, Apache Airflow, or Kafka experience.
Benefits
- Remote-friendly culture.
- Internal training and support for Claude, AWS, and other professional certifications, plus conference attendance.
- Career growth and active engineering development.
- 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 technology needed for productive work.
Tech Stack
Apache AirflowApache KafkaApache SparkAWSAzureGitHub ActionsGitLab CI/CDGoGoogle Cloud PlatformKubernetesPythonRustTypeScript
Categories
Forward Deployed
About Provectus
Provectus is an AI consultancy and solutions provider that designs and implements machine learning, data analytics, MLOps, and generative AI systems for enterprises in finance, insurance, healthcare, retail, media, and manufacturing. It sells consulting engagements and implementation services to help clients adopt AI and cloud platforms in production. Founded in 2010 and headquartered in San Francisco, the company is privately held.