15 days ago
Prague, CzechiaSenior
Responsibilities
- Work alongside an FDE and FDX to build and ship production GenAI, LLM-based, and agentic AI systems in customer environments.
- Build and optimize production RAG systems and evaluation harnesses for non-deterministic AI systems.
- Write production code across AI, backend services, and data pipelines, integrating AI components into backend services and APIs.
- Deploy systems on AWS or other cloud platforms using containers and cloud-native delivery practices.
- Implement LLMOps and AgentOps capabilities including agent tracing, prompt and version management, cost and latency monitoring, regression testing, and drift detection.
- Evaluate models, improve failure modes, and optimize model performance, efficiency, and reliability.
- Contribute to architecture and technical decisions, documentation, runbooks, client handover, and reusable Provectus Blueprints.
- Mentor junior and mid-level AI engineers, conduct code reviews, and share knowledge through documentation, presentations, and workshops.
Requirements
- 5+ years of experience in software or ML engineering with accountability for production systems.
- Strong AI/ML foundations and the ability to reason about model failure modes.
- Experience shipping production LLM applications and agentic workflows, including multi-step orchestration, graph-based workflows, tool use, state management, and recovery from partial failure.
- Experience with LLM APIs, agent frameworks, and production RAG systems.
- Strong engineering fundamentals with a full-stack mindset and proficiency in Python and/or TypeScript.
- Hands-on production AWS experience, including 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 applied to AI pipelines.
- Experience building or owning evaluation suites, defining ground truth, measuring outcomes, and gating releases.
- Experience with model and agent monitoring, drift detection, model tiering, caching, and cost and latency optimization.
- Production experience with Claude, Claude Code, CLAUDE.md, hooks, and skills files is required; spec-driven development is a strong plus.
- Understanding of MCP and experience authoring an MCP server is a plus.
- Excellent communication and problem-solving skills, proactive ownership, comfort with ambiguity, and B2+ English proficiency.
- Preferred qualifications include customer-facing consulting or professional services delivery, AWS or Claude Code certifications, A2A knowledge, GitHub Actions or GitLab CI experience, and experience with NLP, LLMs, recommendation engines, Apache Spark, Apache Airflow, Kafka, Go, TypeScript, or Rust.
Benefits
- Remote-friendly culture.
- Internal training and support for Claude, AWS, and other professional certifications, plus conference attendance.
- Career growth and active engineer development.
- Access to current AI tools and premium subscriptions.
- Long-term B2B collaboration.
- Private medical insurance or a medical-needs budget.
- 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
