AI Engineer

Team.Inno is one of the most experienced Belarusian companies providing full-cycle software development, implementation, and support, business analysis, design, testing, and project management.

For 18+ years, we have completed over 1,600 projects in various industries for clients in the US, Canada, UK, Germany, France, Italy, Japan, and other countries. Our team specializes in 40+ business domains, including Artificial Intelligence, Machine Learning, Augmented & Virtual Reality.

Team.Inno currently has 3,500+ specialists working in offices in Belarus, Poland, Lithuania, Georgia, and Germany. We are constantly seeking experienced and young professionals, and starting in 2025, we will offer free online courses for anyone looking to start a career in IT.

With us, you can try your hand at projects of various sizes, change directions, and choose your career path. Join us!

About the Role
We’re hiring a hands-on AI engineer to build and ship production-ready AI products powered by LLMs and agentic systems. The focus is on engineering the systems, services, interfaces, and integrations that bring LLMs to life in the hands of real users.

Focus: end-to-end ownership — from model selection and prompt engineering through deployment, observability, and iteration — across backend, frontend, and cloud infrastructure.
This role is for engineers who want to build real AI products rather than prototypes, and who use AI as a daily development tool — not “tried Copilot once,” but Claude Code / Cursor as a core part of the workflow.

-What You’ll Be Doing

Build production-ready AI products

→ Develop AI-powered applications integrating LLM capabilities, RAG, and agentic workflows into real-world business processes;

→ Select models, orchestrate prompts, design systems, and implement AI tooling (LangGraph, Langfuse, MCP);

→ Design evaluation, monitoring, and observability for production reliability.

Design and deliver systems

→ Develop scalable, event-driven microservices and APIs — primarily in Python and Node.js / TypeScript or other modern stacks;

→ Build modern, responsive React frontends that make AI useful in customer workflows;

→ Architect cloud-native systems on AWS (Lambda, ECS/Fargate, API Gateway, SQS/SNS, DynamoDB, RDS).

Own delivery end-to-end

→ Take ownership of features from design through to production;

→ Diagnose and improve production behaviors around reliability, latency, cost, and AI quality;

→ Uphold clean code, automated testing, CI/CD, and operational excellence;

→ Communicate directly with clients in English: requirements, technical discussions, demos.

Drive AI-augmented engineering

→ Use AI coding tools (Claude Code and similar) to accelerate development and improve quality;

→ Contribute to defining best practices for AI-assisted software engineering within the team;

→ Mentor teammates, lead code reviews, and raise engineering standards.

What We’re Looking For

Must have:

→ 2+ years of commercial software engineering experience, building and running production-grade applications;

→ Strong hands-on experience with Python (async programming, API development, data pipelines) or with Node.js / TypeScript or another one;

→ Experience with modern frontend frameworks (React, Vue, Angular) or readiness to actively work on the frontend;

→ Experience with prompt engineering, agentic workflows, RAG, and LLM integration;

→ Deep understanding of AWS, cloud-native engineering, APIs, and integration patterns;

→ Experience with microservices, messaging patterns, event-driven and distributed architectures;

→ Daily use of AI coding assistants (Claude Code, Cursor or similar);

→ Awareness of production AI challenges: reliability, latency, cost, hallucinations;

→ Spoken English at B2 level — direct collaboration with clients.

Nice to have:

→ Experience with other backend stacks: .NET / C#, Go, Java, PHP — AI expertise matters more than specific language!

→ Experience with FastAPI, Django, NestJS or similar frameworks;

→ Familiarity with LangGraph, LangChain, Langfuse, CrewAI or other AI orchestration and observability tools;

→ Experience with AI evaluation frameworks and systematic LLM output quality assessment;

→ Experience with MCP (Model Context Protocol) servers;

→ Experience delivering agentic systems in production;

→ Familiarity with AI safety, guardrails, policy enforcement;

→ Background in financial services or regulated environments;

→ Experience with Terraform or CDK;

→ Second foreign language (German strongly preferred).

You’ll thrive if you are:

→ Pragmatic — able to balance speed with long-term quality;

→ Curious about AI, especially safety and responsible usage;

→ Comfortable working in a fast-moving environment with ambiguity;

→ A strong communicator who can explain complex ideas clearly;

→ Passionate about mentoring and raising team standards.

We offer:

Work Environment:

• On-site work format;
• Spacious and comfortable workstations;
• Detailed onboarding: introduction to the team, processes, and policies, office tour, welcome card;
• Cozy kitchens, game rooms, coworking spaces, and lounge areas.

Additional Perks:

• Voluntary health insurance;
• Discounts from partner companies (from pizzerias and bookstores to electronics stores).

If you’re looking for real opportunities to grow professionally and take control of your career — we’ll be happy to welcome you to our friendly team!

The creation of the workplace is planned for the longer term.