Kras AI

AI Engineer

Kras AI

MumbaiPosted 2 months ago
full time
Onsite
0-2 years
Quick Apply
Salary
Not disclosed
Experience
0-2 years
Posted: May 9, 2026
|
Source: internal

Required Skills

Python
Large Language Models (LLMs)
Prompt engineering
Retrieval-Augmented Generation (RAG)
Vector databases (e.g., FAISS/Pinecone)
Model evaluation (test sets, quality metrics)
REST APIs / JSON integration
MLOps basics (logging, monitoring concepts)

About This Role

Overview Kras AI is looking for a Junior AI Engineer to help build and improve AI-powered features using Large Language Models (LLMs) and Python. You’ll work closely with data and engineering teams to prototype, evaluate, and deploy practical AI solutions that enhance customer and internal experiences. Responsibilities - Build and iterate on LLM-based applications and assistants using Python - Develop data processing pipelines to prepare prompts, context, and model inputs - Fine-tune or customize LLM workflows where applicable, following approved guidelines - Evaluate model outputs using relevant metrics and test cases (quality, safety, and reliability) - Integrate AI components with existing services/APIs and handle versioning and logging - Write clean, maintainable code and contribute to documentation and knowledge sharing - Support deployment readiness (monitoring basics, error handling, and incident-friendly logging) Requirements - 0–2 years of experience in AI/ML engineering or building LLM-based applications - Strong Python skills (data handling, scripting, and building application logic) - Hands-on experience with LLMs (prompting, tool-use patterns, RAG basics, or fine-tuning workflows) - Understanding of core ML concepts (training vs. inference, embeddings, evaluation basics) - Familiarity with APIs and integration (REST, JSON, and service-to-service communication) - Comfortable working with datasets and performing basic data validation and preprocessing - Good communication skills and ability to learn quickly in a collaborative environment Nice to have - Experience with retrieval-augmented generation (RAG) using vector databases - Knowledge of model evaluation frameworks and prompt/version testing - Exposure to MLOps practices (model packaging, inference pipelines, monitoring concepts) - Experience with cloud platforms (e.g., AWS) and containerization (Docker) - Awareness of responsible AI practices (bias, hallucination mitigation, and safe prompting) What we offer - Opportunity to build real-world AI solutions in a banking environment - Onsite work in Mumbai with a collaborative engineering culture - Mentorship and learning opportunities as you grow into end-to-end AI development - A chance to contribute to responsible, measurable AI implementations

Create a free account to apply and track your applications