Senior GenAI Engineer

We are seeking a highly skilled Senior GenAI / Agentic AI Engineer with strong hands-on Python development experience and practical expertise building Generative AI, LLM, RAG, and Agentic AI applications.

The ideal candidate will have experience working with OpenAI, Anthropic Claude, Claude Agent SDK, or comparable LLM and agentic frameworks. This individual should understand not only how to use AI models, but also how to design, build, evaluate, and deploy complex AI-enabled applications within an enterprise environment.

Financial Services experience is strongly preferred, particularly within Capital Markets or Fixed Income. The successful candidate should be comfortable working directly with business stakeholders and translating complex workflows into practical AI solutions.

• Strong hands-on experience coding and building applications using Python.
• Strong practical experience with Generative AI, Large Language Models (LLMs), and Agentic AI.
• Experience building AI applications using OpenAI APIs, Anthropic Claude, Claude Agent SDK, or similar LLM platforms and APIs.
• Hands-on experience with agentic frameworks such as LangChain, LangGraph, AutoGen, Semantic Kernel, or similar technologies.
• Strong understanding of Prompt Engineering, including:
  • Prompt design and optimization
  • Prompt testing
  • Grounding
  • Context management
  • Output validation
• Strong hands-on experience implementing RAG (Retrieval-Augmented Generation) solutions.
• Understanding of the components required to build RAG solutions, including:
  • Data ingestion and document processing
  • Chunking strategies
  • Embeddings
  • Vector databases
  • Retrieval and ranking
  • Context generation
  • Response generation and validation
• Experience working with structured and unstructured enterprise data.
• Experience integrating AI applications with APIs, databases, cloud platforms, and enterprise data sources.
• Experience building and supporting complex systems and enterprise-scale applications.
• Experience with MCP (Model Context Protocol) and integrating AI agents with external tools and systems is preferred.
• Experience designing AI evaluation frameworks to measure:
  • Accuracy
  • Relevance
  • Completeness
  • Hallucination risk
  • Consistency
  • Compliance and governance alignment
• Excellent communication and stakeholder management skills.
• Curious mindset with a strong interest in experimenting, learning, and applying emerging AI technologies.