GenAI Engineer with Python

Gen AI Developer is a senior level position responsible for establishing and implementing new or revised application systems and programs in coordination with the Technology team. The overall objective of this role is to lead applications systems analysis and programming activities.

Responsibilities:

Partner with multiple management teams to ensure appropriate integration of functions to meet goals as well as identify and define necessary system enhancements to deploy new products and process improvements

Resolve variety of high impact problems/projects through in-depth evaluation of complex business processes, system processes, and industry standards

Provide expertise in area and advanced knowledge of applications programming and ensure application design adheres to the overall architecture blueprint

Utilize advanced knowledge of system flow and develop standards for coding, testing, debugging, and implementation

Develop comprehensive knowledge of how areas of business, such as architecture and infrastructure, integrate to accomplish business goals

Provide in-depth analysis with interpretive thinking to define issues and develop innovative solutions

Serve as advisor or coach to mid-level developers and analysts, allocating work as necessary

Appropriately assess risk when business decisions are made, demonstrating particular consideration for the firm''s reputation and safeguarding Banking, its clients and assets, by driving compliance with applicable laws, rules and regulations, adhering to Policy, applying sound ethical judgment regarding personal behavior, conduct and business practices, and escalating, managing and reporting control issues with transparency., AI Agent Development: Build and orchestrate AI agents using frameworks like LangChain, AutoGen, or CrewAI, implementing self-healing workflows (e.g., Act-Verify-Refine loops).

LLM Integration & Backend: Develop robust backend systems using Python and TypeScript, integrating LLMs into microservices architectures.

Data Management for LLMs: Utilize vector databases (Pinecone, Milvus, Weaviate) for agent memory and architect Retrieval-Augmented Generation (RAG) pipelines to enhance LLM accuracy and contextual understanding.

Prompt Engineering: Design and optimize prompt strategies, including automated evaluation frameworks, for high-quality LLM output.

Context Engineering: Manage LLM information ecosystems, including system prompts, RAG implementation, and conversation history.

MLOps & Deployment: Oversee the end-to-end lifecycle of generative models, focusing on inference speed, cost-efficiency, and scalability on cloud platforms (AWS, Google Cloud Platform, Azure).

AI Ethics & Compliance: Ensure adherence to security standards, IP regulations, and safety guidelines for all generative models.

Tool Orchestration: Define and manage the API/tool access for AI agents to optimize accuracy.

Experience: 8+ Years in Python and AI (with 2+ year focused on GenAI/Agentic runtime), Technical Proficiency: Strong command of Python, PyTorch, TensorFlow, and Hugging Face libraries.

GenAI Experience: Hands-on experience with LangChain, LlamaIndex, vector databases, and fine-tuning techniques (LoRA, QLoRA).

API & Backend: Proven ability to integrate AI models into web applications via APIs (OpenAI, Anthropic).

Software Engineering: Solid understanding of software engineering best practices, including Git, CI/CD, and Docker.

Preferred Qualifications:

Experience with multimodal AI models (image, video, audio generation).

Published AI/LLM research or contributions to open-source AI projects.

Background in AI governance or safety policy development.

Education:

Bachelor's degree/University degree or equivalent experience