About the Role :

Join the high-impact AI Engineering team of a leading global financial services enterprise. In this hands-on, product-facing role, you will focus on designing and building advanced Retrieval-Augmented Generation (RAG) systems that enable seamless, accurate querying across massive internal document estates. You will play a pivotal role in delivering generative AI solutions and will gain early exposure to cutting-edge, agent-based architectures.

Key Responsibilities :

- LLM & GenAI Development : Build production-grade applications leveraging state-of-the-art models (GPT, Llama, Gemini, Claude); optimize prompt engineering, embeddings, and inference workflows.

- RAG Pipeline Architecture : Design, implement, and maintain high-performing retrieval pipelines, including document chunking, vector search, and response relevance evaluation.

- Agentic Systems : Develop agent coordination, tool integration, and orchestration logic using frameworks such as LangChain or Google ADK.

- Core NLP & Data Pipelines : Build robust NLP pipelines, handle data preprocessing, and establish rigorous model evaluation metrics.

- Production & Deployment : Develop reusable, scalable AI services and REST APIs, containerizing applications using Docker for cloud deployment.

Requirements & Qualifications :

Education : B.Tech / B.E. in Computer Science, Data Science, or a related field.

Experience :

- 5+ years of total software engineering experience.

- 3+ years specifically in Machine Learning and Natural Language Processing (NLP).

- 1.5+ years of hands-on experience building production LLM applications.

Technical Skills :

- Python : Production-grade development with strong coding best practices.

- Vector Databases : Direct experience with at least one vector database/search engine (e.g., Elasticsearch, OpenSearch, FAISS).

- NLP Foundations : Solid grounding in tokenization, embedding techniques, and transformer architectures.

- DevOps & Cloud : Hands-on experience with Docker, microservices architecture, and deployment across major cloud platforms (AWS, Azure, GCP, or OCP).

Nice-to-Have :

- Practical experience with agent workflows and tool-based reasoning paradigms.

- Familiarity with deep learning frameworks (PyTorch, TensorFlow) and MLOps tooling.

- Container orchestration experience with Kubernetes.

- Prior domain exposure to Financial Services or BFSI environments.