Job Description: AI Engineer – LLM & Enterprise AI Solutions (6–8 Years)

Location

Bengaluru / Hybrid

Experience

6–8 years (with 3+ years in AI/ML and at least 1–2 years in GenAI/LLM-based
solutions)

Role Overview

We are seeking an experienced AI Engineer to partner with Data Scientists and
build production-grade AI solutions leveraging Large Language Models (LLMs) and
enterprise knowledge bases. This role focuses on bridging research and
engineering by converting models and prototypes into scalable, secure, and
reliable applications following full SDLC practices.

Key Responsibilities
Collaborate closely with Data Scientists to operationalize ML/AI models into
production systems
Design and develop LLM-powered applications such as copilots, chatbots, and
knowledge assistants
Build Retrieval-Augmented Generation (RAG) pipelines using enterprise data
Integrate AI solutions with knowledge bases, document stores, and vector
databases
Develop end-to-end pipelines for ingestion, embedding, retrieval, and
inference




Ensure adherence to SDLC processes including testing, deployment, and
monitoring
Deploy solutions on cloud platforms with focus on scalability and reliability
Implement MLOps practices including CI/CD, monitoring, and retraining
Ensure security, governance, and responsible AI practices

Required Skills
Hands-on experience with LLMs (OpenAI, Azure OpenAI, Hugging Face)
Robust understanding of RAG, embeddings, prompt engineering
Proficiency in Python / Java and API development
Experience with Java Spring boot / FastAPI/ Flask and microservices
Knowledge of vector databases like FAISS or Pinecone
Experience in SQL, big data technologies (Spark, Redshift), complex data
processing, and data modeling.
Cloud deployment experience (Azure/AWS/GCP)
Familiarity with Docker, Kubernetes, CI/CD

Preferred Qualifications
Experience in enterprise settings
Knowledge of LangChain, LlamaIndex, Semantic Kernel
Understanding of model

📌 Software Engineering Ii Support Services Data Bengaluru
🏢 Kotak
📍 Bengaluru