AI Platform Engineer

About this role

Duration:
6 Months (Potential for extension)


Location:
Remote


Role Overview
We are seeking a seasoned
AI Platform Engineer
to join our Big 4 client to work as a consultant for a major merger of two national banks. You will be responsible for building and optimizing the LLM orchestration layer that will power internal search, data discovery, and automated workflows across the combined entities.


Key Responsibilities

• Engineered Systems: Design and deploy robust embedding pipelines and RAG (Retrieval-Augmented Generation) architectures using LangChain or LlamaIndex.
• Search & Retrieval: Optimize OpenSearch and Vector Database performance to ensure low-latency access to multi-terabyte datasets.
• Model Management: Implement and manage integrations with OpenAI and Anthropic SDKs, ensuring high availability through retry/fallback logic.
• Efficiency & Scaling: Drive token cost optimization strategies and develop streaming interfaces to improve the end-user experience for internal AI tools.
• Advanced Orchestration: Build complex prompt chaining frameworks and implement function calling/tool-use capabilities to allow models to interact with banking APIs safely.

Technical Requirements

• Experience: 5+ years of professional software engineering experience, with a heavy focus on AI/ML infrastructure in the last 2 years.
• Core Languages: Expert-level Python.
• AI Stack: Proven experience with Vector DBs, LangChain, LlamaIndex, and embedding pipelines.
• Systems Design: Deep understanding of LLM-specific patterns:

• Token management and cost-reduction strategies.
• Handling streaming responses.
• Designing resilient retry and fallback models for third-party APIs.

• Data: Strong proficiency with OpenSearch or similar distributed search engines.

Logistics

• Start Date: ASAP
• Duration: Initial 6-month contract with a high likelihood of extension based on project milestones.