Responsibilities
- Ship LLM-powered features using OpenAI, Anthropic, and open-source models
- Design RAG pipelines: embeddings, retrieval, re-ranking, vector DBs
- Engineer prompts, structured outputs, tool use, and guardrails
- Fine-tune transformers with LoRA/QLoRA and PEFT methods
- Build evals to catch hallucinations and regressions
- Optimize models for latency, cost, and scale in production
- Prototype agents, orchestration, and emerging approaches
- Partner with Product, Design, and Engineering on AI delivery
Basic qualifications
- 2+ years hands-on with LLMs and applied AI in production
- 4+ years in software engineering, strong Python
- Transformer architectures and the modern LLM ecosystem (OpenAI, Anthropic, Gemini, Llama, Mistral, Qwen, DeepSeek)
- LangChain, LlamaIndex, or similar LLM frameworks
- Production RAG: embeddings, retrieval, vector DBs
- Prompt engineering, structured outputs, tool use
- Fine-tuning with PEFT (LoRA, QLoRA)
- LLM evaluation and regression testing
- PyTorch or TensorFlow; NumPy, Pandas, scikit-learn
- SQL (PostgreSQL or MS SQL Server)
- Upper-Intermediate+ English level; Native-level Ukrainian language
Preferred qualifications
- Multi-GPU training, computer vision
- AI agents and orchestration (LangGraph, CrewAI, AutoGen)
- Production deployment on AWS, Azure, or GCP
- MLOps and monitoring (LangSmith, W&B, MLflow)
- Research, publications, or AI community involvement
Benefits
- Great company atmosphere and open communication
- 20 working days of vacation and 20 sick days
- Development support
- English classes
- Financial support for learning and sports
- Accounting support
- Membership in Lviv IT Cluster
Tags & focus areas
Used for matching and alerts on DevFound Fulltime Remote Ai Ai Engineer Pytorch Generative Ai