AI Engineer

Overview

The AI Engineer requires hands-on expertise in developing and deploying Large Language Models,

Retrieval Augmented Generation pipelines, and Machine Learning models that support automation,

incident analysis, and operational efficiency. The AI Engineer must demonstrate the ability to design

end-to-end AI workflows, configure vector databases, implement chunking strategies for retrieval, and

build ML models that detect anomalies in logs and system events. The capability includes strong

proficiency in Python, model lifecycle management, prompt engineering, responsible AI practices, and

integrating AI components into production environments.

Job Description:

Build LLM modules for RCA, Incident Summaries, correlation logic, and remediation workflows

using operational data sources such as SOPs, ELK logs, and ServiceNow tickets.

Develop machine learning models to detect anomalies in system and infrastructure logs.

Integrate AI solutions with existing platforms to enhance monitoring, reporting, and

automation capabilities.

Ensure that AI models follow responsible AI practices, governance requirements, and

documentation standards.

Collaborate with cross functional teams to refine AI requirements, support testing, and improve

model outputs.

Requirements:

Relevant Work Experience: The role requires practical experience in developing and deploying

AI systems, including:

Hands-on experience designing transformer based workflows, dynamic prompts, and

LLM driven automation for operational use cases such as incident analysis and RCA.

Experience building tokenization pipelines, embeddings, prompt engineering, and fine

tuning using frameworks such as Hugging Face, LangChain, and OpenAI libraries.

Experience deploying and configuring vector databases for semantic search, including

HNSW indexing, metadata filtering, and sharding using platforms such as Milvus,

Pinecone, or Azure AI Search.

Experience implementing Retrieval Augmented Generation pipelines with chunking

strategies such as semantic chunking, sliding window, or hierarchical chunking.

Experience integrating LLM workflows with enterprise systems such as ELK Stack, SOP

repositories, and ServiceNow tickets.

Experience with ML model lifecycle management including training, evaluation,