Generative AI Engineer (Fresher / Trainee)

Company: CodeArrest Softwares

Work Mode: Remote (India)

Experience: Fresher / 01 year (Strong academic / personal projects are welcome)

Employment Type: Trainee / Internship / Full-Time (depending on fit and performance)

CodeArrest Softwares is hiring Generative AI Engineers (Fresher / Trainee) to support the development of AI-driven applications and internal accelerators. The selected candidate will work closely with senior engineers to build, integrate, and improve features powered by Large Language Models (LLMs) , focusing on practical use cases such as copilots, automation, document intelligence, and workflow enhancements.

This role is suitable for candidates who are technically strong, curious, and motivated to build production-grade AI solutions.

• Assist in designing and developing LLM-based application features and AI workflows.
• Implement and improve prompting strategies , structured outputs, and reusable prompt components.
• Develop RAG (Retrieval Augmented Generation) pipelines using embeddings, chunking, and vector search.
• Integrate AI capabilities into web/services through REST APIs , databases, and application logic.
• Participate in unit testing, basic evaluation of model outputs, and iterative quality improvements.
• Document implementation details, usage guidelines, and technical decisions.
• Collaborate within an agile team environment (planning, updates, reviews, and delivery commitments).

• Bachelors degree (or final year) in Computer Science, IT, or related fields (or equivalent practical experience).
• Strong programming fundamentals in at least one language: Python / JavaScript / TypeScript / C# / Java .
• Basic understanding of APIs, JSON, Git, and software development workflows.
• Familiarity with Generative AI concepts such as:
• prompt structuring
• context windows and tokens
• model parameters (temperature, top-p)
• hallucination awareness and mitigation basics

• Hands-on experience with any of the following:
• LangChain / LlamaIndex / Semantic Kernel
• Vector databases (e.g., FAISS, Pinecone, Weaviate, Milvus) or similar
• Backend frameworks (FastAPI/Flask/Node.js/.NET Web API)
• SQL/NoSQL databases (PostgreSQL, SQL Server, MongoDB)
• Deployment exposure (Docker, Azure/AWS, CI/CD)
• Any project work involving chatbots, AI assistants, summarization, document Q&A, or automation workflows.

• Strong problem-solving skills with the ability to learn quickly.
• Professional communication and documentation habits.
• Ownership mindset, attention to detail, and willingness to iterate to improve solution quality.
• Interest in building reliable AI systems with responsible engineering practices.

• Hands-on exposure to real-world Generative AI implementation in client/product environments.
• Mentorship and structured learning through real delivery work.
• Growth opportunities into AI Engineer / Full-Stack Engineer roles based on performance.
• A collaborative, remote-first work culture.