Solutions Architect, GenAI, Python, AWS

This is a fully remote position, open to applicants in Ukraine.

📋 Description

• Design and develop cloud-native data solutions, leveraging LLM-based and agentic AI technologies to tackle real business challenges faced by clients.

• Implement and enhance RAG systems for production scenarios.

• Foster and maintain robust relationships with key stakeholders, serving as a trusted technical advisor.

• Assist in presales activities, including discovery calls, technical proposals, scoping, and client-facing demonstrations.

• Direct the technical trajectory of client projects from discovery to delivery, acting as the primary authority for both clients and the internal team.

• Write clean, production-ready Python code for AI integrations, backend services, and RESTful APIs.

• Develop and oversee ETL/ELT workflows utilizing contemporary orchestration and distributed computing tools.

• Deploy machine learning and LLM-based solutions.

• Implement practices related to MLOps, LLMOps, and AgentOps, including CI/CD, automated testing, model monitoring, and experiment tracking.

• Lead architecture reviews, create technical design documentation, and contribute to best practices.

• Mentor engineers, conduct code reviews, and disseminate knowledge throughout the team.

⛳️ Requirements

• Possess a full-stack mindset, comfortable working across AI, backend development, and cloud infrastructure.

• Actively utilizing AI tools in your daily workflow (such as Claude Code, Copilot, or similar).

• Proactive and self-driven; take ownership of outcomes from start to finish and identify issues before they escalate.

• Proficient in English (B2+) and comfortable collaborating with distributed, multicultural teams.

• Manage the client’s technical relationship by leading discovery, breaking down ambiguous requirements into technical components, presenting architecture, and addressing scope issues when they misalign with timelines or budgets.

• Create scoped, phased delivery plans with well-defined deliverables, dependencies, and risks.

• Over 7 years of experience in building and managing production systems, beyond just demos and POCs.

• Hands-on experience in developing production-level LLM-based applications and agentic workflows.

• Proficient in integrating AI/ML components into various solutions.

• Familiarity with LLM APIs (e.g., OpenAI, Anthropic, or AWS Bedrock).

• Experience in constructing and optimizing RAG systems.

• Understanding of LLM evaluation techniques and quality assurance methods.

• Proven experience in deploying and managing AI/ML models in production settings.

• Python expertise in OOP, design patterns, clean architecture, and performance enhancement.

• Experience in developing RESTful APIs using FastAPI, Django REST, or Flask.

• Skilled in making and defending architectural trade-off decisions.

• Familiar with Docker and Kubernetes.

• Hands-on experience with AWS (including Bedrock AgentCore, Bedrock, Lambda, ECS, S3, SQS, ECR, or similar); GCP experience is also considered.

• Knowledge of CI/CD practices applicable to ML and AI pipelines.

• Familiarity with model monitoring, observability, and drift detection techniques.

🏝️ Benefits

• Opportunity to engage with advanced AI and cloud solutions.

• Access to internal training programs (Leadership, Public Speaking, etc.) with comprehensive support for AWS and other professional certifications.

• Career development: a clear advancement path towards SA or higher; we are dedicated to nurturing our engineers' growth.

• Access to the latest AI tools and premium subscriptions.

• Long-term B2B collaboration.

• Work remotely with flexible hours.

• Private medical insurance or a budget for your medical needs.

• Paid sick leave, vacation, and public holidays.

• Provision of equipment and all necessary technology for a comfortable and productive work environment.