AI/LLM Engineer

Job Description – AI/LLM Engineer (RAG & Agentic Systems)

We are seeking a highly motivated AI/LLM Engineer to join a growing team focused on building next-generation generative AI solutions within the banking and financial services domain. This role will focus on designing and productionizing Retrieval-Augmented Generation (RAG) pipelines, agentic AI systems, and LLM-powered applications that interact with financial and structured enterprise data.

The team is open to strong early-career candidates, including recent graduates with exceptional academic backgrounds, internships, or impactful AI/ML projects.

Key Responsibilities

• Design, extend, and optimize RAG pipelines, retrieval strategies, embedding workflows, and semantic search capabilities.
• Build and productionize agentic AI architectures that orchestrate across:
  • RAG workflows
  • Structured SQL/data retrieval
  • External APIs and downstream actions (e.g., report/PPT generation)
• Fine-tune and evaluate LLMs using model adaptation techniques, prompt engineering, and inference optimization.
• Implement model safety mechanisms, guardrails, hallucination mitigation, and response validation strategies.
• Develop and maintain APIs, endpoints, and tooling for model serving, observability, monitoring, and versioning.
• Partner with SQL/data engineering teams to securely integrate structured enterprise data into LLM workflows.
• Design reusable retrieval templates and interfaces for enterprise-scale AI applications.
• Implement testing frameworks and monitoring for:
  • Latency
  • Accuracy
  • Hallucination rates
  • Cost efficiency
  • Retrieval quality
• Participate in architecture and vendor-selection discussions focused on scalability, performance, and cost optimization.

Required Skills

• Hands-on experience building production-grade RAG pipelines and agentic AI systems.
• Strong experience with LLM fine-tuning, model adaptation, or custom inference workflows.
• Deep understanding of at least one LLM orchestration framework such as:
  • LangChain
  • LlamaIndex
  • Similar orchestration frameworks
• Strong Python development and API engineering experience.
• Ability to clearly explain:
  • System architecture decisions
  • Tool/framework selection
  • Dataset preparation
  • Evaluation methodologies
  • Deployment and productionization strategies
• Experience working on AI/ML projects such as:
  • Chatbots
  • Financial AI applications
  • Intelligent document/query systems

Nice-to-Have Skills

• Experience integrating LLMs with relational or structured databases.
• Familiarity with vector databases and embedding stores such as:
  • Pinecone
  • Milvus
  • Weaviate
  • Oracle vector/embedding capabilities
• Knowledge of:
  • Prompt engineering
  • Retrieval augmentation
  • LLM safety
  • Hallucination mitigation
  • Guardrail implementation
• Experience with cloud infrastructure, model hosting, and monitoring in distributed environments.
• Exposure to Kubernetes, serverless architectures, and AI infrastructure cost optimization.
• Java experience is a plus for interoperability with enterprise systems.

Preferred Background

• Banking, financial services, fintech, or enterprise AI environments.
• Strong academic background in Computer Science, AI/ML, Data Science, or related fields.
• Candidates with standout internships, research, or hands-on AI projects are highly encouraged to apply.