Backend Engineer, AI Agent Systems

About the Position

We are seeking a Backend Engineer specializing in AI systems to join our remote team in Warsaw, Poland, building scalable backend systems for an AI-native personal assistant.

About the Product

Our client is developing an AI-native assistant designed to support everyday communication, organization, errands, and complex workflows with minimal user input. The product must reliably manage long-running processes, retain context, interact with external tools, and complete real-world tasks despite the non-deterministic nature of modern AI models. The company’s objective is to make everyday activities significantly faster and easier for users.

Responsibilities

• Build and operate backend systems serving AI-powered functionality in production.
• Design inference pipelines, orchestration layers, and service boundaries around Machine Learning models.
• Take ownership of production monitoring, logging, alerting, and incident response.
• Optimize latency and throughput across inference, caching, batching, and streaming.
• Build reliable APIs supporting integration with mobile, frontend, and Machine Learning systems.
• Diagnose distributed-system issues under production load.
• Continuously improve system performance and reliability using real-world production signals.

Requirements

• Strong backend engineering fundamentals supported by experience with production systems.
• Experience building or operating high-throughput, low-latency services.
• Familiarity with AI inference patterns, including LLMs, embeddings, and multimodal models.
• Confidence debugging distributed systems under load.
• Understanding of production observability, incident management, and performance optimization.
• A delivery-oriented mindset focused on shipping, observing production behavior, and improving through iteration.
• Ability to work independently and make pragmatic engineering decisions in an ambiguous environment.

Technology Stack

• Python
• Node.js
• PyTorch
• OpenAI, Anthropic, and open-source LLMs
• SQL and NoSQL databases
• Kubernetes
• Docker

We Offer

• Compensation: Assessed individually based on professional experience, technical capability, scope of responsibility, location, relevant market benchmarks, and expected impact on the product and organization.
• Equity: Compensation package consists of a base salary and equity, with flexibility for exceptional candidates.
• Remote Work: The company operates as a remote-first, globally distributed organization. Team members are expected to maintain sufficient working-hours overlap with their immediate colleagues to collaborate effectively.
• Global Collaboration: The successful candidate will work from Poland and collaborate with backend, Machine Learning, mobile, and product specialists located across different regions.

About the Company

Talentica’s client is a remote-first, globally distributed technology company developing an AI-native personal assistant for communication, organization, errands, and complex real-world workflows. Its mission is to make everyday activities substantially faster and easier through dependable AI that can retain context, use external tools, and manage long-running tasks. The company emphasizes small, highly capable hands-on teams, collaborative decisions, individual ownership, pragmatic execution, experimentation, production quality, and continuous learning from real user behavior.

Recruitment Process

The standard recruitment process consists of up to four stages:

1. Technical assessment, where relevant to the candidate’s background.
2. HR interview.
3. One or more technical interviews.
4. Founder or leadership interview.

Particularly strong candidates may be fast-tracked directly to the technical interview stage based on their experience and previous work.

Applications are evaluated by members of the technical team. Interviews may be conducted virtually and, where relevant, onsite. The exact format and interviewers may vary.

The company aims to make decisions efficiently and provide candidates with a prompt outcome.