Junior/Middle Software Engineer with AI Experience

🟠 Details: we are looking for a Junior/Middle Software Engineer with hands-on experience building applications powered by Large Language Models (LLMs) such as GPT, Claude, Gemini, and similar technologies.

The role focuses on developing production-oriented AI features, improving Retrieval-Augmented Generation (RAG) systems, integrating LLM APIs, and working with embeddings, semantic search, retrieval quality, and response optimization.

You’ll be successful in this role if you enjoy experimenting with AI systems, improving retrieval quality, and turning LLM capabilities into reliable product features.

🟠 Qualifications:

• 1–3 years of experience with Python or TypeScript as a primary programming language.
• Experience building applications powered by LLMs (GPT, Claude, Gemini, etc.) in commercial, pet, or research projects.
• Strong understanding of RAG concepts, embeddings, semantic search, chunking, and retrieval optimization.
• Experience building or maintaining RAG pipelines.
• Familiarity with vector databases (Pinecone, Weaviate, Qdrant, FAISS, Chroma, or similar).
• Experience with OpenAI API / SDK or other LLM providers.
• Understanding of LLM evaluation approaches, hallucination mitigation, and response quality improvement.
• Familiarity with LLM orchestration frameworks (LangChain, LangGraph, LlamaIndex, or similar).
• Understanding of token/context limitations, tool calling, and structured outputs.
• Experience with SQL databases, Git, CI/CD, and Linux environments.
• English language proficiency at B2 level (upper-intermediate) and above.

🟠 Would be a plus:

• Experience with AWS, GCP, Azure, or Cloudflare.
• Familiarity with monitoring and evaluation tools (LangSmith, Grafana, Helicone, etc.).
• Experience with NLP, AI agents, fine-tuning workflows, or evaluation datasets.
• Knowledge of Docker, Kubernetes, or microservices.

🟠 Responsibilities:

• Develop and improve AI-powered features using embeddings, semantic search, retrieval optimization, and LLM integrations.
• Build and maintain RAG pipelines and retrieval systems.
• Work with vector databases and semantic search infrastructure.
• Design and improve reliable integrations with OpenAI and other LLM providers.
• Participate in R&D, evaluation, and experimentation tasks related to AI systems.
• Collaborate with engineers to deliver scalable and reliable AI-powered services.

🟠 Interview steps:

• Screening with the recruiter (about 45 minutes).
• Take-home task.
• Technical interview with the CEO (about 30 minutes).
• Optional live coding session with a Python or TypeScript Developer (about 1 hour).

🟠 By joining us, you will get:

• 15 paid vacation days + 30 unpaid days off per year.
• 4 paid public holidays.
• 5 sick leaves.
• Accounting and legal support.
• Flexible hours, remote work, and quality equipment.
• 100% certification coverage (on success).
• 50% coverage for additional training.
• Internal workshops and knowledge sharing.
• $50/month wellbeing budget (50% co-pay) for sport, education, therapy, and massage.
• Team-buildings, gifts, and company events.
• Internal rewards and perks program.

🟠 Our office:

📍 FuturaHUB, located in Lviv (Kulparkivska 200a).

• Modern and comfortable workspace.
• Conference rooms and chill-out areas.
• Sports activities and team events.
• Coffee, tea, snacks, and more.

🟠 Some of our values:

• Healthy work-life balance.
• No overtime or pressure culture.
• Transparent communication and clean relationships.
• Ownership and initiative.
• Openness to experimentation, learning, and change.