Generative AI Engineer – Data & AI - Institutional Equities

Role Summary:

The GenAI Engineer will design, build, and deploy generative AI applications and retrieval-based systems within the enterprise data and AI ecosystem. The role involves working with LLMs, embeddings, vector search, orchestration frameworks, and backend services to create scalable, production-ready AI components. The engineer will collaborate with ML, Data Engineering, and Cloud teams to integrate GenAI capabilities across various business and technical workflows.

Key Responsibilities:

- Build and maintain GenAI applications, including LLM-powered assistants, automation workflows, and RAG-based solutions.

- Design and implement embedding pipelines, chunking strategies, vector indexing, and retrieval logic.

- Work with vector databases for storage, search, and semantic retrieval.

- Develop backend APIs and services using Python and frameworks like FastAPI.

- Implement prompt engineering, evaluation, testing, and optimisation processes.

- Integrate GenAI components with enterprise data and cloud platforms (AWS, Databricks, or similar).

- Build orchestration flows using LangChain, LlamaIndex, or equivalent tools.

- Ensure reliability, observability, and structured logging for GenAI workloads.

- Collaborate with cross-functional teams to convert requirements into AI-enabled solutions.

- Maintain documentation for design decisions, workflows, prompts, and deployment pipelines.

Required Skills:

- Strong Python

- Hands-on experience with GenAI frameworks such as LangChain, LlamaIndex, or similar.

- Solid understanding of embeddings, vector databases, similarity search, and retrieval optimization.

- Experience with LLM APIs (OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, etc.).

- Ability to build scalable GenAI services using FastAPI or equivalent frameworks.

- Understanding of prompt design, evaluation methods, and guardrail techniques.

- Experience with cloud integration (AWS preferred) for deploying AI components.

- Familiarity with unstructured data handling and preprocessing.

Good-to-Have Skills:

- Exposure to MLOps tools (Mlflow, model registry, deployment workflows).

- Basic understanding of Spark / PySpark for scalable preprocessing.

- Familiarity with multi-agent frameworks (CrewAI, AutoGen, LangGraph).

- Understanding of containerization (Docker) and CI/CD pipelines.

- Experience working with enterprise data platforms or analytics ecosystems.