AI Engineer

Job Description

Day to Day: Insight Global is seeking an AI Engineer to join one of our largest financial services clients supporting a rapidly growing AI product team within Global Markets. This team is responsible for developing and scaling enterprise AI solutions, agent-based applications, and Generative AI platforms that support business transformation initiatives across the bank. This individual will work across the full AI product lifecycle, helping design, develop, and enhance internal AI tools focused on Retrieval-Augmented Generation (RAG), prompt engineering, model evaluation, agent development, and AI-powered operational intelligence. The engineer will partner closely with product owners and architects to determine how data should be ingested, structured, searched, and leveraged to solve complex business challenges.

The team is currently expanding due to growing demand and increasing adoption of internally developed AI products. One of the team's flagship platforms enables users to perform model design, prompt engineering, document chunking, vector scoring, retrieval evaluation, and AI application development. Additional initiatives include intelligent document transformation, operational automation, telemetry analysis, anomaly detection, and next-generation agent-based architectures leveraging MCP frameworks.

Key Responsibilities: • Design and develop scalable AI applications and reusable AI tooling using Python and FastAPI • Build and optimize RAG solutions, including chunking strategies, embedding selection, metadata tagging, vector search, hybrid search, and retrieval evaluation • Partner with stakeholders to understand data sources, identify meaningful indicators, and create AI-driven solutions for anomaly detection and intelligent decision support • Evaluate and select appropriate models based on use case requirements, performance metrics, cost considerations, and governance requirements • Develop effective prompts, structured outputs, and retrieval strategies to improve model accuracy and reduce hallucinations • Build API integrations and AI-enabled services while adhering to enterprise security and authentication standards • Participate in architecture reviews, solution design discussions, testing exercises, and model approval processes • Support the evolution of Agent-based and MCP-enabled solutions, including observability, governance, and operational intelligence capabilities • Collaborate across engineering and product teams to deliver AI solutions that improve operational efficiency, scalability, and business outcomes • Analyze complex technical challenges and provide recommendations around architecture, implementation approach, risk, and time-to-market considerations

Skills and Requirements

Must Haves: • 3+ years of hands-on Python development experience with strong Object-Oriented Programming (OOP) fundamentals • Experience building and deploying Generative AI, RAG, and LLM-based solutions in production environments • Strong knowledge of RAG architecture including: • Chunking strategies • Metadata tagging • Embedding selection • Vector search • Hybrid search • Retrieval quality optimization • RAG evaluation • Experience with prompt engineering, token management, context windows, hallucination reduction, and model selection • Experience building API-driven applications using FastAPI and REST services • Understanding of AI/ML lifecycle management, inference frameworks, MLOps, and model tuning techniques • Ability to architect AI solutions from concept through implementation, balancing business value, scalability, performance, and time-to-market • Experience with enterprise development tools including Git, CI/CD pipelines, Ansible, Jira, Confluence, and multi-repository development environments • Knowledge of security and authentication frameworks including JWT, API Gateways, SSO, and OWASP standards Plusses: • Experience with MCP (Model Context Protocol) and Agent-based architectures • Elastic search experience, particularly around anomaly detection and AI-driven search use cases • Experience building AI gateways, observability frameworks, or enterprise inference platforms • AWS Cloud experience • Exposure to ServiceNow and large-scale enterprise transformation initiatives • Experience working with telemetry, operational, infrastructure, or monitoring data sets • Exposure to model governance, model risk management, and enterprise AI approval processes

We are a company committed to creating diverse and inclusive environments where people can bring their full, authentic selves to work every day. We are an equal employment opportunity/affirmative action employer that believes everyone matters. Qualified candidates will receive consideration for employment without regard to race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request to View email address on click.appcast.io.