About us - Software lab - Flyps is a high-tech software house with nearly a decade of experience turning complex technical challenges into production-ready products. - Clutch 5.0 ⭐⭐⭐⭐⭐ from satisfied customers! - Products we helped build were later acquired! - (recent exits to Cursor, SpaceX, LlamaIndex, PE) - Work with serial entrepreneurs, SF startups, and established businesses that want to stay ahead of market shifts. - A highly experienced team, with in-house PhDs and most senior engineers. - Work at the technological frontier: - An actively developed internal AI harness with access to leading models. - Infrastructure for experimenting with local models but don’t worry, we haven’t lost our heads and gone all-in on tokenmaxxing :) The role We’re looking for an experienced Senior Applied AI Engineer to build and improve production AI systems, combining strong software engineering with hands-on experience working with LLMs. You’ll work on systems where AI quality needs to be measurable - from agentic workflows and LLM applications to evaluation, debugging, and production reliability. You’ll investigate problems, design experiments, choose the right technical approach, and verify whether a change actually improves the system. You’ll also provide technical direction to other engineers, helping the team make sound architectural decisions, develop their skills, and evaluate new technologies based on practical results rather than demos What you’ll do - Design and develop LLM-powered systems, from prototypes to production. - Diagnose and improve AI systems by analysing code, data, logs, and execution traces. - Choose the right approach, from simple workflows to agentic architectures. - Build evaluations and regression tests to measure quality and detect failures. - Run experiments to compare solutions across quality, cost, latency, and reliability. - Build backend services and API integrations, including validation, error handling, logging, and monitoring. - Work with clients to define requirements and acceptance criteria, and communicate technical decisions, results, and limitations. - Set technical direction, review solutions, and support engineers through mentoring and collaborative problem-solving. - Evaluate new models, tools, and approaches and validate their practical value before recommending them for production. What we’re looking for - Strong software engineering skills with experience building production applications. - Hands-on experience with LLM-powered systems, including LLM APIs, tool calling, structured outputs, and multi-step workflows. - Experience with RAG, vector search, or agent-based architectures. - Experience building backend services and APIs, preferably with FastAPI, plus automated testing, Git, and code review. - Practical experience with LLM evaluation and observability - measuring quality, failures, latency, and cost. - Strong technical problem-solving skills and ability to make sound architectural trade-offs. - Experience providing technical guidance through architecture decisions, code reviews, and mentoring. - Strong communication skills - you can explain technical decisions, challenge assumptions, and work effectively with clients and engineers. - Comfortable using AI-powered coding assistants such as Cursor, GitHub Copilot, ChatGPT, or Claude. - Comfortable working in a bilingual environment (Polish C2 and English C1). What we offer - 26 000 - 33 000 PLN net + VAT monthly, B2B - 100% remote setup and flexible hours - Private medical care, life insurance, and Multisport 🏃♂️➡️ - Referral bonuses - Equipment (MacBook by default) - Interesting, challenging projects - we only take on the ones we believe in :-)
Summary
Build and improve production LLM systems, from prototypes to production, including agentic workflows, evaluations, backend services, and client requirements. Requires strong software engineering, hands-on LLM API and tool-calling experience, RAG or agent architectures, backend/API development, observability, and bilingual Polish C2/English C1 communication.
Responsibilities
Design and develop LLM systems; diagnose and improve AI systems; choose workflows or agentic architectures; build evaluations and regression tests; run quality, cost, latency and reliability experiments; build backend services and API integrations; define client requirements; provide technical direction, reviews and mentoring; evaluate new models and tools
Qualifications
Strong software engineering and production application experience; hands-on LLM systems with APIs, tool calling, structured outputs and workflows; RAG, vector search or agent architectures; backend/API development; LLM evaluation and observability; technical guidance and mentoring; strong communication; bilingual Polish C2 and English C1
Experience requirements
Production software engineering with LLM-powered systems, backend services/APIs, evaluation/observability, and technical mentoring
Benefits
Private medical care, life insurance, Multisport, referral bonuses, equipment (MacBook by default)