AI Engineer (LLM / Generative AI)

About Bitmedia Labs
Bitmedia Labs - an international product IT company, has been in the industry since 2014, effectively functioning on a worldwide scale with a crew of 130+ ambitious and highly skilled professionals, creating successful projects in domains such as online advertising systems for the crypto space, blockchain games, and NFT products.

We are currently looking for an experienced engineer to join our R&D project, contributing to cutting-edge development and innovation within the company.

Required Qualifications:
 

• 3+ years of software engineering experience, with 2+ years working with LLMs and generative AI
• Strong Python development skills in a production environment (clean code, typing, testing, Git)
• Experience with both proprietary (OpenAI, Anthropic, Gemini) and open-source LLMs (LLaMA, Mistral)
• Working knowledge of orchestration frameworks (LangChain, LlamaIndex)
• Hands-on experience building RAG pipelines and working with vector databases (Pinecone, Weaviate, Qdrant, pgvector, or similar)
• Experience with model fine-tuning techniques (LoRA, QLoRA, PEFT) and understanding of when to fine-tune vs. use RAG or prompt engineering
• Practical prompt engineering skills: structured outputs, function/tool calling
• Experience building backend services and APIs (FastAPI or Flask)
• Solid SQL skills and experience with databases (PostgreSQL, MongoDB, Redis, or Elasticsearch)
• Ability to debug LLM-specific issues (hallucinations, retrieval quality, cost/latency), work independently, and communicate technical decisions clearly.
   

Preferred Qualifications:
 

• Experience with agentic workflows and multi-step orchestration (LangGraph, CrewAI)
• Cloud deployment experience (AWS, GCP, or Azure), Docker, CI/CD
• Open-source model serving and inference optimization (vLLM, TGI, quantization, caching)
• Advanced retrieval techniques: hybrid search, reranking, query rewriting
• Familiarity with LLM evaluation and observability tools (RAGAS, DeepEval, LangSmith, Arize Phoenix)
• Knowledge of AI safety practices: prompt-injection prevention, PII handling, guardrails.

Hiring process: 
 

• Intro call with a Recruiter - Technical Interview with the Hiring team - Collection of Recommendations - Offer.
   

We offer:

• Flexible work environment - you can work remotely from anywhere;
• The 8-hour working day with a flexible schedule;
• Competitive salary based on your experience;
• Regular performance review and annual salary review;
• Paid sick leaves, vacation, and holidays;
• Professional development tools (reimbursement of educational courses or workshops, conferences around the world);
• Ambitious team with transparent communication and a friendly atmosphere, no micromanagement;
• Apple equipment;
• Memorable gifts for holidays.