Why do we need you?

At Appsilon, we empower global organizations to make smarter decisions with data. Our solutions help Fortune 500 companies discover new drugs, save lives, optimize operations, and unlock millions in value. To do this, we rely on robust, scalable, beautifully engineered data systems.

We're looking for an AI Engineer who combines strong engineering fundamentals with hands-on experience building and deploying AI agents and generative AI solutions - someone who can design agentic workflows that deliver real value in production.

What you’ll do:

• Build AI Agents with domain context for specialized tasks, including multi-step reasoning, tool use, and autonomous decision-making.

• Design and implement agentic workflows — orchestrating LLMs, retrieval systems, and external tools into reliable, production-grade pipelines.

• Integrate agents with client applications, APIs, and enterprise systems.

• Evaluate, iterate on, and optimize agent performance using structured testing, tracing, and observability.

• Deploy and maintain generative AI solutions in production environments (APIs, microservices, cloud architecture).

• Document your work, follow best practices for LLMOps, and help shape AI development standards at Appsilon.

• Work closely with Data Engineers, Developers, and Analysts to integrate GenAI solutions into full-scale applications.

  We’re looking for someone with:

• Proven experience building and deploying AI agents or agentic systems in production (not just prototypes).

• Deep familiarity with LLM orchestration frameworks (e.g., LangChain, LangGraph, CrewAI, Autogen, Claude Agent SDK, or similar).

• Strong understanding of prompt engineering, retrieval-augmented generation (RAG), tool use, and function calling patterns.

• Hands-on experience with LLM APIs (OpenAI, Anthropic, Google, open-source models) and managing their lifecycle in real-world applications.

• Strong programming skills in Python with experience building robust, maintainable backend services.

• Ability to evaluate and debug agent behavior - including tracing, logging, and structured evaluation of multi-step workflows.

• Excellent communication skills and a collaborative approach to teamwork.

Nice to have:

• Experience with cloud deployment (AWS, Azure, GCP) and containerization (Docker / Kubernetes).

• Knowledge of vector databases (Pinecone, Weaviate, Qdrant, pgvector) and embedding pipelines.

• Familiarity with LLMOps and observability tools (LangSmith, Langfuse, Weights & Biases, etc.).

• Background in classical ML (scikit-learn, PyTorch, TensorFlow) and understanding of the model training lifecycle.

• Experience working with large-scale or scientific datasets (biostatistics, genomics, pharma).

• Understanding of AI ethics, bias, and responsible AI principles.

What we offer:

• 100% remote work, flexible schedule, and a global team culture.

• Competitive B2B compensation with transparent ranges.

• Work on impactful, real-world products used by enterprise clients and scientific industries.

• Budget and dedicated time for professional development (courses, certs, conferences).

• A chance to collaborate with a brilliant group of researchers and industry experts.

• Modern equipment and tools for efficient development.

• Supportive environment with room for innovation, experimentation, and ownership.

Important note: To complete the hiring process, you need to have a valid government-issued ID (for Polish citizens) or a valid passport (for non-Polish citizens).

Recruitment Process

• General interview with the People Team.

• Technical task (Codility test). 

• Technical interview

• Final interview with the Head of Technology

• Offer.

Does this sound like a great opportunity for you?

Use the Apply button below!

Appsilon is committed to being a diverse and inclusive workplace. We encourage applicants of different backgrounds, cultures, genders, experiences, abilities, and perspectives to apply. All qualified applicants will receive consideration for employment without regard to race, color, national origin, religion, sexual orientation, gender, gender identity, age, physical disability, or length of time spent unemployed.