Skip to main content

Solutions Architect (AI, Python/Data)

Provectus · Tbilisi ·

Full-time

Job description

Solutions Architect (AI, Python/Data)
Company: Provectus
Location: Yerevan / Belgrade / Novi Sad, Vojvodina / Tbilisi
Type: Full-time

\n

What You’ll Do:

-
Design and build cloud-native data, LLM-based, and agentic AI solutions addressing real client business challenges

-
Implement and optimize RAG systems for production use cases

-
Build and maintain strong relationships with key customer stakeholders, acting as a trusted technical advisor.

-
Support presales: discovery calls, technical proposals, scoping, and client-facing demos

-
Own the technical direction of client engagements from discovery through delivery — the go-to authority for clients and the internal team

-
Write clean, production-grade Python across AI integrations, backend services, and RESTful APIs

-
Build and maintain ETL/ELT workflows using modern orchestration and distributed computing tools.

-
Deploy ML and LLM-based solutions

-
Implement MLOps, LLMOps, and AgentOps practices: CI/CD, automated testing, model monitoring, and experiment tracking.

-
Lead architecture reviews, produce technical design documents, and contribute to standards

-
Mentor engineers, lead code reviews, and share knowledge across the team.

What You’ll Bring:
Mindset

  • Full-stack mindset, comfortable across AI, backend development, and cloud infrastructure
  • Already using AI tools in your daily workflow (Claude Code, Copilot, or similar)
  • Proactive and self-directed; you own outcomes end-to-end and spot problems before they're handed to you
  • B2+ English, comfortable collaborating across distributed, multicultural teams

Presales & Client Engagement

  • Owns the client technical relationship; leading discovery, decomposing ambiguous requirements into technical components, presenting architecture, and pushing back on scope when it doesn't match timeline or budget
  • Produces scoped, phased delivery plans with clear deliverables, dependencies, and risks
  • Experience with cost estimation and cloud architecture cost optimization

AI & Python/ Data & Cloud

  • 7+ years building and running production systems — not only demos and POCs
  • Hands-on experience building production LLM-based applications and agentic workflows
  • Experience in integrating AI/ML components into solutions
  • Experience with LLM APIs (OpenAI, Anthropic, or AWS Bedrock)
  • Experience building and optimizing RAG systems
  • Understanding of LLM evaluation techniques and quality assurance approaches
  • Experience deploying and maintaining AI/ML models in production environments
  • Python skills: OOP, design patterns, clean architecture, and performance optimization
  • Experience building RESTful APIs with FastAPI, Django REST, or Flask
  • Experience in making and defending architectural trade-off decisions
  • Experience with Docker and Kubernetes
  • Hands-on experience with AWS (Bedrock AgentCore, Bedrock, Lambda, ECS, S3, SQS, ECR, or similar); GCP considered
  • Understanding of CI/CD practices applied to ML and AI pipelines
  • Familiarity with model monitoring, observability, and drift detection.

Nice to Have

  • AWS and Claude Code Certifications
  • CI/CD pipeline experience (GitHub Actions, GitLab CI)
  • Experience in an additional language (Go, Node.js, or Rust).
  • Hands-on experience with Apache Spark, Apache Airflow, Kafkа

What We Offer:

  • Opportunity to work with cutting-edge AI and cloud solutions
  • Internal training programs (Leadership, Public Speaking, and more) with full support for AWS and other professional certifications
  • Career growth: a clear path toward SA or beyond; we actively develop our engineers
  • Access to the latest AI tools and premium subscriptions
  • Long-term B2B collaboration
  • Remote with flexible hours
  • Private medical insurance or a budget for your medical needs
  • Paid sick leave, vacation, and public holidays
  • Equipment and all the tech you need for comfortable, productive work

\n

Want the next one first?

Apply on the original posting → (opens in a new tab)