Generative AI Engineer

Role Overview

We are seeking an AI Engineer with strong hands-on experience in Large Language Models (LLMs) and Generative AI to build, deploy, and optimize enterprise-grade AI applications. The ideal candidate is passionate about applying cutting-edge AI technologies to real business use cases in a highly collaborative and innovative environment.

Key Responsibilities

Develop and integrate LLM-powered solutions such as chatbots, automation tools, and summarization systems.

Build and maintain RAG pipelines, embeddings, and retrieval workflows.

Apply prompt engineering, guardrails, and model optimization techniques.

Design and deploy scalable APIs/microservices using Python (FastAPI/Flask).

Deploy AI solutions on AWS / Azure / GCP using Docker & Kubernetes.

Collaborate with data, product, and engineering teams to deliver production-ready AI applications.

Stay updated on the latest AI advancements (Hugging Face, LangChain, LlamaIndex, OpenAI, Anthropic, Mistral, Meta Llama).

Required Skills

Strong proficiency in Python with hands-on API development.

Proven experience developing and delivering LLM/GenAI solutions.

Knowledge of Hugging Face Transformers, LangChain, LlamaIndex, etc.

Experience with vector DBs (FAISS, Pinecone, Weaviate, Milvus).

Solid understanding of RAG architecture and embedding models.

Experience with cloud platforms (AWS/Azure/GCP), Docker, Kubernetes.

Strong analytical mindset and ability to collaborate across teams.

Nice to Have

Experience in financial services or regulated environments.

Exposure to CI/CD pipelines and cloud-native architectures.

Familiarity with agent workflows, multi-step orchestration, LangGraph.