About

Hello, I am looking for an experienced LLM / GenAI Engineer to help design, build, and optimize AI-driven features for our product. The ideal candidate has deep experience working with large language models, building AI pipelines, and integrating AI capabilities into production systems. *** Must be native or bilingual English *** PLEASE include introduction video describing AI experience about 1 or 2 mins. Any proposal without this video will be ignored. Salary will be increased upto 4K USD if result is good. Responsibilities - Architect and implement AI workflows using LLMs and multimodal models (OpenAI, Anthropic, Llama, custom fine-tuned models) - Build AI orchestration pipelines for tasks such as reasoning, routing, planning, retrieval, tool use, and automation - Develop embeddings, vector search, and Retrieval-Augmented Generation (RAG) pipelines - Fine-tune or adapt models using LoRA, instruct tuning, or domain-specific data - Integrate AI features into backend services (Python, FastAPI, Node.js, or similar) - Optimize performance, latency, and reliability for real-world usage - Implement monitoring, evaluation, and guardrails for AI systems - Collaborate with product and engineering teams to turn business requirements into functional AI features - Produce clean technical documentation and maintain code quality Requirements - Strong experience with LLMs (OpenAI, Claude, Gemini, Llama, Mistral, etc.) - Proficiency in Python and modern AI frameworks (PyTorch, LangChain, LlamaIndex, FastAPI) - Experience with RAG pipelines, vector databases (Pinecone, Weaviate, Milvus, pgvector) - Deep understanding of prompt engineering, prompt optimization, and model orchestration - Knowledge of agentic workflows, tool-calling, and multi-step reasoning - Familiarity with fine-tuning techniques and model evaluation - Experience deploying AI solutions to production environments - Strong problem-solving, architectural thinking, and communication skills