Lead / Senior NLP Engineer

About

EdSpan is an innovative company in the EdTech space, building cutting-edge learning experiences for the next generation of students. Our collaboration with a US-based private school network helps us better understand user needs while expanding our B2C and B2B products to a broader audience. We are currently working on three major projects:

AI tutoring experience — an innovative project that brings real-time interaction with a 3D animated assistant powered by LLM technology. This virtual tutor helps students navigate challenges, provides guidance, and enhances the learning journey in a playful and engaging way.

Tutorpeers – a peer-to-peer tutoring platform with a young teachers marketplace, event booking features and Zoom-like online sessions with additional interactive learning tools.

Spark Incubator – LMS-like system designed to teach kids entrepreneurship.

We have well-defined processes, trying to automate routine things, conduct code reviews, use CI and CD pipelines to validate and ship our code. We use the Agile approach with daily stand-ups, bi-weekly sprints, and other Scrum artifacts. We keep the number of meetings to a minimum so that engineers can focus on writing high-quality code and delivering cool features.

Who you are

We’re hiring our first AI/ML Engineer to lead the development of our AI agents, including prompting, the RAG and evaluation pipelines, potential fine-tuning. So, you’ll play a key role in shaping the technical direction. We’re seeking someone with a strong understanding of machine learning and NLP fundamentals, capable of tackling complex challenges in agentic workflows and optimizing model performance across the stack.

Requirements

• At least 4 years of experience in the field of Machine Learning, working as a Data Engineer, Data Scientist, Machine Learning Engineer, or in a similar role.
• Bachelor’s degree in Computer Science, Mathematics, or equivalent practical experience;
• Proficiency in Python and common data science libraries (pandas, NumPy, scikit-learn);
• In-depth knowledge of machine learning principles, understanding of LLM architectures, prompt optimization, and fine-tuning strategies;
• Skilled in designing and optimizing RAG pipelines, including embedding generation, sparse and dense retrieval, and hybrid search techniques;
• Familiar with LLM evaluation metrics and tools (BLEU, RAGAS, DeepEval, and other);

• Upper-Intermediate level of English (B2) or above.

   

Highly desireable

• Proven experience building AI-driven workflows using frameworks such as LangGraph, AutoGen, or similar orchestration tools;

• Knowledge of AWS cloud and MLOps.

   

Responsibilities

• Design, implement, and optimize LLM prompts to ensure reliable outputs;
• Assist in developing and maintaining AI evaluation workflows, including designing evaluation guidelines and metrics;
• Help design and develop AI data pipelines: collection, storage, annotation, and model improvement;
• Leverage agent orchestration tools to improve and automate AI workflows;
• Collaborate with the product team to ensure AI capabilities power usable product features.