AI Software Engineer

AI Software Engineer
Primary objective: Build, test and operate AI services and pipelines for DocTutorials under defined engineering and responsible-AI standards.

The AI Software Engineer will implement practical LLM, RAG and AI automation capabilities and work with senior engineers, Product and application teams to deliver production-ready outcomes.
Key Responsibilities

1. AI Development

• Develop AI services and APIs using Python and FastAPI.
• Implement document processing, embeddings, vector search, retrieval and prompt workflows.
• Integrate approved LLMs and AI services with DocTutorials applications.
• Build tests, error handling and monitoring for AI pipelines.

1. Quality and Responsible AI

• Evaluate outputs for relevance, groundedness, consistency, safety and latency.
• Maintain source traceability and human-review controls where required.
• Protect learner, content and organisational data throughout development.
• Track experiments, prompts, models, datasets and configuration changes.

1. Collaboration and Growth

• Work with application engineers, QA, Product and domain experts.
• Participate in design reviews, code reviews and incident analysis.
• Learn production AI patterns, MLOps/LLMOps and cost optimisation.
• Take ownership of assigned AI components through production support.

Required Skills and Experience

• 2+ years of software, data or AI engineering experience.
• Strong Python fundamentals and API-development exposure, preferably FastAPI.
• Hands-on knowledge of LLMs, RAG, embeddings and vector databases.
• Basic experience with LangChain, LlamaIndex, Haystack or similar frameworks.
• SQL, Git, testing, Docker and cloud fundamentals.
• Practical understanding of Generative AI, LLMs, RAG, Agentic AI and responsible AI use relevant to the role.
• Ability to use approved AI tools productively while protecting source code, credentials, learner data and organisational information.
• Commitment to human review, testing, security validation and traceability for AI-assisted outputs.

Good-to-Have Experience

• Machine learning, NLP, model serving or fine-tuning exposure.
• AWS, Kubernetes, MLOps/LLMOps or observability.
• EdTech or medical-learning experience.

How Success Will Be Measured

• Assigned AI services function reliably in production.
• Evaluation and testing identify quality issues early.
• Data and security standards are followed consistently.
• Technical independence and AI engineering depth improve.
• Work consistently delivers measurable outcomes

Expected mindset: Own the outcome, use AI responsibly, communicate risks early and deliver secure, measurable value for DocTutorials and its learners.