Вакансія Senior Data Engineer AI/ML

Skills

• RAG
• OpenSearch
• Elasticsearch
• Python
• LlamaIndex
• LangChain
• Pinecone
• Qdrant
• FAISS
• LLM
• AWS
• Azure
• GCP
• Docker
• Kubernetes

Опис вакансії

Our mission at Geniusee is to help businesses thrive through tech partnership and strengthen the engineering community by sharing knowledge and creating opportunities. Our values are Continuous Growth, Team Synergy, Taking Responsibility, Conscious Openness and Result Driven. We offer a safe, inclusive and productive environment for all team members, and we’re always open to feedback. If you want to work from home or work in the city center of Kyiv, great – apply right now.

Requirements

• 8+ years of experience in software engineering, with a focus on AI/ML systems or distributed systems;
• Hands-on experience building and deploying retrieval-augmented generation (RAG) systems;
• Deep knowledge of OpenSearch, Elasticsearch, or similar search engines;
• Strong coding skills in Python;
• Experience with frameworks like LlamaIndex or LangChain;
• Familiarity with vector databases such as Pinecone, Qdrant, or FAISS;
• Exposure to LLM fine-tuning, semantic search, embeddings, and prompt engineering;
• Previous work on systems handling millions of users or queries per day;
• Familiarity with cloud infrastructure (AWS, GCP, or Azure) and containerization tools (Docker, Kubernetes);
• Experience with vector search, embedding pipelines, and dense retrieval techniques;
• Proven ability to optimize inference stacks for latency, reliability, and scalability;
• Excellent problem-solving, analytical, and debugging skills;
• Strong sense of ownership, ability to work independently, and a self-starter mindset in fast-paced environments;
• Passion for building impactful technology aligned with our mission;
• Bachelor’s degree in Computer Science or related field, or equivalent practical experience.

What you will do

• Design, build and scale a production-grade inference stack for RAG-based applications;
• Develop efficient retrieval pipelines using OpenSearch or similar vector databases, with a focus on high recall and response relevance;
• Optimize performance and latency for both real-time and batch queries;
• Identify and address bottlenecks in the inference stack to improve response times and system efficiency;
• Ensure high reliability, observability, and monitoring of deployed systems;
• Collaborate with cross-functional teams to integrate LLMs and retrieval components into user-facing applications;
• Evaluate and integrate modern RAG frameworks and tools to accelerate development;
• Guide architectural decisions, mentor team members, and uphold engineering excellence.