Talentica

iOS Software Engineer

Remote · Posted 4h ago

salary not listedpermanentremote
LLMRAG

Job Description

About the productOur 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.About the roleWe are looking for a Full Stack Engineer specializing in AI systems to build the product layer that transforms advanced AI capabilities into useful, production-grade workflows.You will help design how AI agents plan and operate, interact with external tools, manage failures, recover from errors and deliver consistent value to users.This is an end-to-end engineering role covering frontend development, backend systems and AI integrations.What you will doBuild end-to-end product functionality across frontend, backend and AI integrations.Design agent workflows covering planning, tool use, multi-step execution, failure handling and recovery.Integrate LLMs, memory systems and external tools into applications that operate reliably under real-world conditions.Design real-time AI interactions involving streaming, partial results and strict latency requirements.Improve system reliability, observability and fallback mechanisms.Collaborate closely with Machine Learning, backend and product teams to deliver functionality from concept to production.Continuously improve the product based on real-world usage, evaluation results and observed failure modes.What we are looking forStrong professional experience in full stack engineering across frontend and backend systems.Solid understanding of system design, distributed applications and API architecture.Experience working with LLMs, RAG systems or other AI-powered applications.Ability to operate effectively in ambiguous situations and make pragmatic engineering decisions.Strong ownership and the ability to take functionality from an initial idea through implementation and production deployment.Confidence working in a fast-moving environment with evolving product requirements.Ability to collaborate effectively across engineering, Machine Learning and product teams.What success looks likeAI-native product features progress beyond basic chat interfaces into persistent, goal-oriented workflows.Agent workflows reliably complete multi-step tasks across external tools and multiple user sessions.AI interactions remain responsive and achieve low latency without compromising output quality.Production systems include robust fallback and recovery mechanisms for LLM and external-tool failures.The reliability and completion rate of AI workflows improve through continuous evaluation, monitoring and iteration.Reusable patterns and abstractions support scalable integration of LLMs, memory and external tools.The resulting product experience feels proactive, consistent and dependable to users.Technology stackNext.jsPythonNode.jsPyTorchOpenAI, Anthropic and open-source LLMsSQL and NoSQL databasesKubernetesDockerCompensation and employmentThe position is offered under an employment contract.The company does not publish a fixed external salary range. Compensation is assessed individually based on:professional experience and technical capability,scope of responsibility,location and relevant market benchmarks,expected impact on the product and organization.Candidates may share their expected compensation at the beginning of the recruitment process. The compensation package consists of a base salary and equity, with flexibility for exceptional candidates.A company laptop will be provided where required for the role.Remote work and global collaborationThe company operates as a remote-first, globally distributed organization.There is no fixed company-wide working schedule and no requirement to follow one specific time zone. Team members are expected to maintain sufficient working-hours overlap with their immediate colleagues to collaborate effectively.The successful candidate will work from Poland and collaborate with frontend, backend, Machine Learning and product specialists located across different regions.Poland-based employees join existing global teams rather than a separate local team. The exact reporting line and hiring manager will be confirmed during the recruitment process.How the team worksThe company believes that outstanding products are built by small, highly capable and hands-on teams. Decisions are made collaboratively, while individuals are expected to take ownership, bring structure to ambiguous problems and execute independently.The team moves quickly while balancing production quality, experimentation and continuous learning from real user behavior.There is no fixed hiring quota for this position. The company is focused on identifying engineers who meet its technical and ownership standards rather than filling a