LLM Application Engineer
⚲ Warszawa
Do uzgodnienia
Wymagania
- Python
- LLM
- RAG
- Langchain
- fastapi
- vector databases
Opis stanowiska
LLM Application Engineer
About the Company
Our client is a remote-first global AI product company building a proactive smart assistant for everyday users. The product brings intelligence to conversations, everyday tasks, organization, and workflows while requiring minimal prompting.
The platform is designed to reliably execute long-running workflows, retain persistent context, and complete real-world tasks. It must support multi-step reasoning, interact with external tools, and remain dependable despite the non-deterministic nature of modern AI models.
The goal is to make everyday tasks easier, faster, and more intuitive through practical AI experiences used by people around the world.
About the Role
As an LLM Application Engineer, you will build the intelligence layer powering the company’s AI experiences.
You will work at the intersection of LLMs, software engineering, and product—designing agent workflows, improving model behavior, and turning AI capabilities into reliable user experiences.
You will own problems end-to-end: understanding user needs, designing agentic workflows, integrating models and tools, building evaluation systems, and continuously improving AI behavior in production.
Your Responsibilities
• Build and ship LLM-powered applications and AI agent workflows.
• Design systems for reasoning, planning, memory, tool use, and multi-step execution.
• Build reliable orchestration pipelines that turn probabilistic model outputs into predictable, observable, and safe actions.
• Integrate LLMs with APIs, databases, search systems, internal services, and external tools.
• Develop prompting, context engineering, structured outputs, tool calling, and other techniques that improve model behavior.
• Build evaluation frameworks and datasets to measure AI quality, reliability, and regressions.
• Debug AI systems across the entire stack—from model behavior and prompts to orchestration, backend services, and product UX.
• Optimize AI systems for quality, latency, and cost.
• Work closely with product and engineering teams to turn ambiguous product problems into working AI solutions.
• Establish production practices for observability, tracing, experimentation, evaluation, and continuous improvement.
Tech Stack
• Python
• LLM APIs and model providers, including OpenAI-compatible APIs and open-weight models
• Agent frameworks and orchestration systems
• Vector databases and retrieval systems
• Backend services, APIs, and distributed systems
• PyTorch / JAX
Ideal Experience
• Strong software engineering fundamentals and experience building AI-powered applications.
• Hands-on experience with LLMs, generative AI, or agent-based systems.
• Experience designing prompts, agent workflows, evaluations, or AI behavior.
• Ability to write clean, production-quality code.
• Comfort working across abstraction layers—from models and infrastructure to backend systems and product experiences.
• Strong problem-solving skills in ambiguous, fast-moving environments.
• Ownership mentality and the ability to take an AI feature from concept to production.
• Bias toward shipping, iteration, and continuous improvement.
Expected Outcomes
• AI features reach production quickly and deliver measurable value to users.
• LLM-powered workflows are reliable, scalable, observable, and maintainable.
• AI quality improves through systematic evaluation, experimentation, and iteration.
• AI workflows become increasingly predictable, efficient, and cost-effective.
• Complex AI capabilities are translated into simple and intuitive user experiences.
• Production issues are identified, investigated, and resolved using clear observability and evaluation signals.
Employment and Working Model
• Polish employment contract.
• Fully remote position for candidates based in Poland.
• You will join an existing global team and collaborate with colleagues across different regions.
• There is no fixed company-wide schedule or requirement to work in one specific time zone.
• Sufficient overlap with your immediate teammates is required for effective collaboration.
• A company laptop will be provided where required for the role.
• The compensation package consists of a base salary and equity.
• Compensation is assessed individually based on experience, technical capability, expected impact, and relevant market benchmarks.
• Candidates are invited to share their expected gross monthly salary in PLN.
Interview Process
The standard recruitment process consists of:
• Technical assessment, where relevant.
• HR interview.
• Technical interview or interviews.
• Founder or leadership interview.
The process normally includes three and no more than four interviews. Particularly strong candidates may be fast-tracked directly to the technical stages. The exact interviewers and assessment format may vary.
Applications are reviewed by the technical team. Interviews are conducted remotely, and candidates can expect a transparent and efficient decision-making process.
The recruitment process is managed by Talentica on behalf of the client.
About the Company
Our client is a remote-first global AI product company building a proactive smart assistant for everyday users. The product brings intelligence to conversations, everyday tasks, organization, and workflows while requiring minimal prompting.
The platform is designed to reliably execute long-running workflows, retain persistent context, and complete real-world tasks. It must support multi-step reasoning, interact with external tools, and remain dependable despite the non-deterministic nature of modern AI models.
The goal is to make everyday tasks easier, faster, and more intuitive through practical AI experiences used by people around the world.
About the Role
As an LLM Application Engineer, you will build the intelligence layer powering the company’s AI experiences.
You will work at the intersection of LLMs, software engineering, and product—designing agent workflows, improving model behavior, and turning AI capabilities into reliable user experiences.
You will own problems end-to-end: understanding user needs, designing agentic workflows, integrating models and tools, building evaluation systems, and continuously improving AI behavior in production.
Your Responsibilities
• Build and ship LLM-powered applications and AI agent workflows.
• Design systems for reasoning, planning, memory, tool use, and multi-step execution.
• Build reliable orchestration pipelines that turn probabilistic model outputs into predictable, observable, and safe actions.
• Integrate LLMs with APIs, databases, search systems, internal services, and external tools.
• Develop prompting, context engineering, structured outputs, tool calling, and other techniques that improve model behavior.
• Build evaluation frameworks and datasets to measure AI quality, reliability, and regressions.
• Debug AI systems across the entire stack—from model behavior and prompts to orchestration, backend services, and product UX.
• Optimize AI systems for quality, latency, and cost.
• Work closely with product and engineering teams to turn ambiguous product problems into working AI solutions.
• Establish production practices for observability, tracing, experimentation, evaluation, and continuous improvement.
Tech Stack
• Python
• LLM APIs and model providers, including OpenAI-compatible APIs and open-weight models
• Agent frameworks and orchestration systems
• Vector databases and retrieval systems
• Backend services, APIs, and distributed systems
• PyTorch / JAX
Ideal Experience
• Strong software engineering fundamentals and experience building AI-powered applications.
• Hands-on experience with LLMs, generative AI, or agent-based systems.
• Experience designing prompts, agent workflows, evaluations, or AI behavior.
• Ability to write clean, production-quality code.
• Comfort working across abstraction layers—from models and infrastructure to backend systems and product experiences.
• Strong problem-solving skills in ambiguous, fast-moving environments.
• Ownership mentality and the ability to take an AI feature from concept to production.
• Bias toward shipping, iteration, and continuous improvement.
Expected Outcomes
• AI features reach production quickly and deliver measurable value to users.
• LLM-powered workflows are reliable, scalable, observable, and maintainable.
• AI quality improves through systematic evaluation, experimentation, and iteration.
• AI workflows become increasingly predictable, efficient, and cost-effective.
• Complex AI capabilities are translated into simple and intuitive user experiences.
• Production issues are identified, investigated, and resolved using clear observability and evaluation signals.
Employment and Working Model
• Polish employment contract.
• Fully remote position for candidates based in Poland.
• You will join an existing global team and collaborate with colleagues across different regions.
• There is no fixed company-wide schedule or requirement to work in one specific time zone.
• Sufficient overlap with your immediate teammates is required for effective collaboration.
• A company laptop will be provided where required for the role.
• The compensation package consists of a base salary and equity.
• Compensation is assessed individually based on experience, technical capability, expected impact, and relevant market benchmarks.
• Candidates are invited to share their expected gross monthly salary in PLN.
Interview Process
The standard recruitment process consists of:
• Technical assessment, where relevant.
• HR interview.
• Technical interview or interviews.
• Founder or leadership interview.
The process normally includes three and no more than four interviews. Particularly strong candidates may be fast-tracked directly to the technical stages. The exact interviewers and assessment format may vary.
Applications are reviewed by the technical team. Interviews are conducted remotely, and candidates can expect a transparent and efficient decision-making process.
The recruitment process is managed by Talentica on behalf of the client.
🔍 Dekoder Ogłoszenia
🔴
requiring minimal prompting
System może wymagać bardziej złożonych instrukcji niż sugeruje opis, lub użytkownicy będą musieli nauczyć się specyficznych sposobów interakcji.
🔴
own problems end-to-end
Oczekuje się pełnej odpowiedzialności za projekt, od koncepcji po wdrożenie i utrzymanie, co może oznaczać szeroki zakres obowiązków.
🟡
designing agent workflows
Może oznaczać zarówno tworzenie prostych sekwencji wywołań modeli, jak i bardziej złożonych, autonomicznych agentów, co wymaga różnych umiejętności.
🟡
turning AI capabilities into reliable user experiences
Podkreśla trudność w przekształceniu eksperymentalnych możliwości AI w stabilne i przewidywalne produkty dla użytkowników końcowych.
🔴
continuously improving AI behavior in production
Wskazuje na ciągłe debugowanie i dostosowywanie modeli AI po ich wdrożeniu, co może być czasochłonne i wymagać głębokiego zrozumienia działania modeli.