LLM / Agentic AI Engineer

About the job

THIS IS A 6-MONTH CONTRACT POSITION WITH ONE OF THE LARGEST GLOBAL TECHNOLOGY LEADERS. We are looking for a highly skilled LLM / Agentic AI Engineer to design and build production-grade AI systems powered by Large Language Models. You will architect intelligent, multi-agent workflows, implement advanced RAG pipelines, and deploy enterprise-ready AI solutions working with finance and large-scale datasets. This role requires strong expertise in LLM engineering, retrieval systems, agent orchestration, and cloud-native deployment practices. Primary Skills - AI/ML, LLM, Python, Snowflake/SQL Secondary Skills - Agentic AI, MCP Qualifications• 3+ years of relevant experience in AI/ML or applied LLM engineering.• Strong hands-on experience with Python and SQL (Snowflake preferred). • Proven experience building LLM-powered applications using OpenAI (GPT-4/4.1), Anthropic, Gemini, or Llama models. • Experience implementing RAG pipelines including embeddings, chunking strategies, hybrid search, and vector databases. • Hands-on experience with LangChain, LangGraph, tool calling, and agent frameworks. • Solid understanding of hallucination mitigation techniques including grounding, re-ranking, citations, and confidence scoring. • Experience working with structured and unstructured enterprise datasets. • Bachelor’s degree in Computer Science, Engineering, or related field (or equivalent practical experience). Preferred Qualifications• Experience designing Agent-to-Agent (A2A) architectures for multi-step reasoning and autonomous workflows. • Hands-on experience with MCP (Model Context Protocol) and agent memory/state management. • Experience using evaluation and observability tools such as LangSmith, MLflow, or Weights & Biases. • Strong understanding of prompt/version management and offline/online LLM evaluation techniques. • Experience deploying AI systems on AWS (S3, Lambda, SageMaker, Bedrock). • Experience implementing CI/CD pipelines for AI inference services and model workflows. • Exposure to DBT and modern data transformation pipelines. • Experience building scalable, monitored, and cost-optimized AI systems in production environments. Responsibilities• Design and build LLM-powered chatbots and AI applications using OpenAI APIs, RAG pipelines, and agent frameworks. • Architect and implement multi-agent (A2A) systems for complex reasoning and workflow automation. • Design and optimize retrieval systems using embeddings, hybrid search, and vector databases. • Implement techniques to reduce hallucination and improve output reliability through grounding and evaluation frameworks. • Work with finance and enterprise data ensuring accuracy, governance, and compliance. • Deploy, monitor, and optimize AI systems using cloud-native infrastructure and MLOps best practices. • Implement CI/CD pipelines for AI workflows and inference services. • Continuously evaluate and improve prompt performance, model responses, latency, and cost efficiency.

Requirements

• AI/ML
• LLM
• Python
• SQL
• Agentic AI

Qualifications

• Bachelor’s degree in Computer Science, Engineering, or related field

Preferred Technologies

• AI/ML
• LLM
• Python
• SQL
• Agentic AI

About the company

Our client is a Fortune-ranked global technology leader, renowned for innovation and engineering excellence. They foster a culture of collaboration, technical depth, and continuous learning, empowering engineers to build next-generation solutions that impact millions of users worldwide. The organization values integrity, diversity, and curiosity, creating an environment where technology professionals can thrive and innovate freely.