About the role
You will join the AI engineering team of a large global financial services enterprise. Your core focus will be designing and building retrieval-augmented systems that allow users to accurately query massive internal document estates. This is a hands-on, product-facing role with early exposure to emerging agent-based architectures.
Responsibilities:
- LLM and GenAI: Build applications using GPT, Llama, Gemini, or Claude; optimise prompts, embeddings, and inference workflows.
- RAG Pipelines: Develop and maintain high-performing retrieval pipelines (chunking, vector search, response relevance).
- Agentic Systems: Implement agent coordination, tool integrations, and orchestration logic using LangChain or Google ADK.
- Core NLP: Design and implement NLP pipelines, data preprocessing, and model evaluation metrics.
- Deployment: Build reusable, scalable AI services and REST APIs using Docker and Cloud platforms.
Requirements:
- Experience: 5+ years in software engineering, with 3 years in ML/NLP and 1.5+ years building LLM applications.
- Python: Production-grade, strong coding skills.
- Vector DBs: Hands-on with at least one (Elasticsearch, OpenSearch, FAISS, etc. ).
- NLP Foundations: Solid grounding in tokenisation, embeddings, and transformers.
- DevOps: Experience with Docker, microservices, and any major cloud (AWS, Azure, GCP, OCP).
Nice-to-Have:
- Experience with agent workflows and tool-based reasoning.
- Familiarity with PyTorch, TensorFlow, MLOps tooling, or Kubernetes.
- Exposure to the Financial Services / BFSI domain.