Senior Backend & AI Engineer (Python)

Location: Warsaw, PL We support tech companies in building engineering teams in Poland. For this role, we act as a recruitment partner supporting the hiring process on behalf of our customer. Our customer is a fast-growing, VC-backed HR-tech startup. Their product helps people automate their job search, from finding relevant roles to preparing applications. ‍ The team you’ll join works on one of the product’s features: an AI career coach that helps candidates assess their skills and prepare for interviews. You’ll work closely with product managers, designers and front-end engineers. We’re looking for a Senior Backend & AI Engineer (Python) to help build and develop the core architecture from scratch and ship the entire product. You’ll own technical decisions for the backend architecture, APIs and microservices, and build AI agents and stateful LLM conversational flows. ‍ As the company scales, you’ll also help establish engineering best practices, code quality standards and technical documentation. Design and implement scalable, secure, and efficient back-end services primarily in Python. Architect and develop advanced AI agents and stateful LLM conversational flows, managing short-term session context and long-term memory extraction. Build logic to evaluate user interactions and implement structured data pipelines to save, transcribe, and serve real-time session histories and system analytics. Own technical decisions for backend architecture, APIs, and microservices design. Explore and evaluate new tools, frameworks, and infrastructure to improve the product and infrastructure stack. Collaborate closely with product managers, designers, and front-end engineers to deliver impactful features. Proactively identify tech issues, lead the research, and resolve complex architectural bottlenecks. Help establish engineering best practices, code quality standards, and technical documentation as we scale. ‍ 5+ years of experience in back-end development with Python. Proven hands-on experience building AI agents, orchestrating complex LLM workflows, and deploying RAG pipelines. Experience with advanced AI orchestration and memory management frameworks (e.g., LangGraph, LangMem) Experience with Vector Search Engines (such as Qdrant) for high-performance data retrieval and artifact management. Experience with latency optimization for LLM streaming and database queries. Strong ownership: ability to do independent research, problem-solve, and unblock yourself autonomously. Strong knowledge of PostgreSQL and experience working with Object-Relational Mappers (ORMs). Experience in early-stage startups or building systems from scratch in a fast-paced environment. Proactive and highly autonomous, yet disciplined – you don’t wait to be told what to do, but you like and respect established team processes, are able to maintain organized workflows, and value a structured engineering environment. Result-oriented, hard-working with high ambitions. Strong English (B2 or higher). ‍ Experience with TypeScript, NestJS, or React, and a willingness to contribute across the stack if necessary. Knowledge of CI/CD pipelines and containerization with Docker. Experience with message brokers (e.g., NATS) for microservices communication. Experience in performance optimization and working with high-load or data-intensive systems. Expertise with subscription-based or B2B/B2C SaaS. ‍ The benefit package will be discussed individually during the interview process.