4 months ago
Tbilisi, GeorgiaSenior
Responsibilities
- Embed with clients and the Forward Deployed Executive to understand workflows, redesign functions, and identify business problems.
- Design, build, optimize, and deploy production GenAI, LLM-based, agentic, and RAG systems.
- Build evaluation harnesses, define quality criteria, instrument systems, and use evaluation results to guide releases.
- Write production code across AI systems, backend services, and data pipelines.
- Deploy and maintain cloud-native systems with containers, CI/CD, automated testing, monitoring, and maintainability requirements.
- Lead architecture reviews, technical design documentation, standards, technical proposals, and engagement scoping.
- Own technical direction, adoption, change management, client handover, and contribution to reusable Blueprints.
- Mentor engineers, share knowledge, and collaborate with customer engineers and executives.
Requirements
- At least 7 years of experience building and running production systems.
- Strong AI/ML foundations and understanding of model capabilities and failure modes.
- Experience designing and shipping production LLM applications and agentic workflows, including orchestration, tool use, state management, and recovery from partial failure.
- Experience with Anthropic, AWS Bedrock, or OpenAI APIs; agent frameworks; and production RAG systems.
- Proficiency in Python and/or TypeScript, with the ability to work productively in unfamiliar codebases or languages.
- Experience making and defending architectural trade-offs and producing scoped delivery plans with costs, dependencies, and risks.
- Hands-on AWS production 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, CI/CD, model and agent monitoring, drift detection, model tiering, caching, and cost and latency optimization.
- Experience building or owning evaluation suites for non-deterministic systems and defining ground truth and release gates.
- Production experience with Claude Code, CLAUDE.md, hooks, skills files, and MCP; MCP server authorship and spec-driven development are valued.
- Strong client-facing communication, stakeholder credibility, self-direction, comfort with ambiguity, and B2+ English.
- Nice-to-have experience includes founder, CTO, or engineering leadership work; financial services, insurance, or healthcare; consulting or professional services; A2A interoperability; AWS or Claude Code certifications; GitHub Actions or GitLab CI; Go or Rust; Apache Spark, Apache Airflow, or Kafka.
Benefits
- Remote-friendly culture.
- Long-term B2B collaboration.
- Private medical insurance or a medical-needs budget.
- Paid sick leave, vacation, and public holidays.
- Equipment and technology provided.
- Internal training and support for Claude, AWS, and other professional certifications, plus conference attendance.
- Career growth and access to the latest AI tools and premium subscriptions.
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.