AI Engineer – LLM Applications & Agents
We're Hiring: AI Engineer
We’re looking for someone who can design and build AI agents, retrieval-augmented generation (RAG) systems, and LLM-based applications that solve real-world business problems. If you thrive on experimenting with the latest frameworks and turning them into production-ready systems, this might be the role for you.
You’ll have space to take ownership, shape ideas from the ground up, and actually see the impact of what you build. Sound like the kind of role you’re looking for? Then we’d love to meet you.
Who are we?
Hi 👋 We’re Striveonlab – a team solving real problems through data, AI, and automation. We focus on end-to-end AI solutions, from structuring messy data and designing retrieval systems to developing AI agents that automate real tasks and integrate into live products.
Our clients range from e-commerce brands to startups and growing companies looking to scale with confidence.
What you’ll be doing
Design and implement LLM-based applications and AI agents – from early discovery to production-ready systems, either independently or in a focused team.
Build and orchestrate AI agents and multi-agent workflows (LangChain, LangGraph, or similar) that automate real tasks and integrate into live products.
Develop and deploy retrieval-augmented systems (RAG, Graph-RAG) and pipelines for unstructured data (text, forms, logs, user inputs).
Prototype and validate ideas quickly, then evolve them into stable, scalable solutions.
Work directly with clients to understand their needs, shape ideas, and translate them into technical solutions.
Contribute to standards for testing, evaluation, and guardrails to ensure LLM apps are reliable in production.
Contribute to early-stage discovery – evaluate technical feasibility, design system architecture (agents, retrieval, data pipelines), prototype quickly, and help shape realistic time estimates.
Stay on top of the latest developments in LLMs, agent frameworks, evaluation methods, and prompting strategies, and apply them thoughtfully.
Collaborate with a cross-functional team (designers, devs, product owners) to ensure the AI solution actually fits into the broader product or workflow.
Think beyond code: understand the business context, identify risks, and help us deliver solutions that actually work in production.
What we’re looking for
Must-have
Strong Python skills & 3+ years of software engineering experience, ideally with at least 1–2 years focused on AI/LLM development
Hands-on experience building LLM-based applications from prototyping to production
Practical experience with agent frameworks (LangChain, LangGraph, or similar)
Familiarity with retrieval systems (vector databases, RAG pipelines, embeddings, chunking, re-ranking)
Experience deploying AI services to cloud platforms
Strong problem-solving skills and the ability to give and receive thoughtful feedback
Confidence working directly with clients and making technical decisions
Clear communication skills – able to explain complex ideas to both technical and non-technical stakeholders
Comfort working in ambiguity and iterating fast toward working solutions
A sense for product thinking: you care not just about writing code, but about building something useful
Nice-to-have
Experience with multi-agent orchestration
Knowledge of evaluation frameworks, guardrails, and prompt optimization
Broader ML/DS background (NLP, recommendation, classical ML) that helps in applied projects
Interest in experimenting with new frameworks, runtimes, or infra approaches
What we offer
Flexible work setup – contract-based (project, part-time, or more), hybrid (3 days in our Praga Studios office in Prague / 2 days remote), or fully remote if needed. It’s not about where you sit, it’s about what you deliver.
Purpose-driven projects – connecting data, AI, and business to solve real-world challenges
Room to grow – whether you want to go deeper into AI, lead projects, or explore new directions
Influence over company direction – if you see something worth improving, you can make it happen
Transparent leadership and direct communication – a culture of trust, clarity, and focus, no micromanagement here.
Support for your curiosity – learning budget, space to explore new tools and approaches, and teammates who love sharing knowledge
Sound like a match?
Send us your CV, portfolio/GitHub, or just a quick note telling us why we should talk.
Looking forward to hearing from you,
The Striveonlab team