Assist in developing AI-powered features using Python, LLM tools, ML libraries, APIs, and internal platform services.
Support prompt engineering, prompt testing, model comparison, and evaluation of AI-generated outputs.
Help build and maintain RAG workflows, including document preparation, chunking, metadata tagging, embedding generation, retrieval testing, and result review.
Prepare, clean, format, and validate datasets used for model testing, prompt evaluation, and AI experiments.
Assist with model and workflow evaluation by reviewing outputs, identifying errors, documenting patterns, and comparing performance across approaches.
Write clean, readable Python code for scripts, internal tools, prototypes, experiments, and service components.
Support debugging of AI workflows, data pipelines, API integrations, and model behavior under the guidance of senior engineers.
Participate in code reviews, design discussions, team planning, and documentation efforts.
Learn and apply production engineering practices, including Git workflows, testing, logging, Docker, CI/CD, and deployment basics.
Document experiments, implementation details, findings, and recommendations clearly for technical team members.

0–2 years of experience in AI engineering, machine learning, software engineering, data science, or a related technical area.
Internship experience, academic work, bootcamp projects, portfolio projects, or open-source contributions are acceptable.
Solid Python programming skills.
Foundational understanding of machine learning, deep learning, NLP, data processing, and model evaluation concepts.
Familiarity with tools or libraries such as PyTorch, TensorFlow, scikit-learn, Hugging Face Transformers, pandas, NumPy, or similar technologies.
Interest in LLMs, GenAI systems, prompt engineering, embeddings, semantic search, RAG, and AI agents.
Ability to work with structured and unstructured data.
Comfort using Git, notebooks, command-line tools, APIs, and collaborative development workflows.
Strong attention to detail, curiosity, problem-solving ability, and willingness to learn from feedback.
Clear written communication skills for documenting technical work and experiment results.

Junior AI Engineer

Key skills