Generative AI Engineer

Role Overview

We are looking for a passionate Generative AI Engineer with hands-on experience in building production-ready LLM applications, RAG pipelines, AI backend services, and intelligent document or vision systems. The ideal candidate should be comfortable working across model fine-tuning, prompt engineering, vector databases, and scalable API development.

Responsibilities

• Design, develop, and deploy LLM/SLM-based applications using LangChain, LangGraph, OpenAI, and Hugging Face.
• Build and optimize RAG pipelines with vector databases such as Pinecone or FAISS.
• Fine-tune transformer models using LoRA, Unsloth, and Hugging Face Transformers.
• Develop scalable backend services using Python, FastAPI, REST APIs, and GraphQL.
• Implement async processing and performance optimization for high-traffic AI services.
• Work on OCR, document AI, speech-to-text, and computer vision pipelines where required.
• Deploy AI workloads using Docker, GCP Vertex AI, AWS S3, and Kubernetes.
• Collaborate with product, frontend, and engineering teams to deliver production-grade AI systems.
• Maintain technical documentation, version control, and deployment workflows.

Requirements

• 1+ year of experience in Generative AI / AI Engineering.
• Strong proficiency in Python.
• Experience with LangChain, OpenAI APIs, Hugging Face, RAG, and Prompt Engineering.
• Knowledge of Vector Embeddings, Pinecone, or FAISS.
• Experience with FastAPI, REST APIs, and async programming.
• Familiarity with Docker and cloud platforms (GCP or AWS).
• Understanding of model quantization, ONNX, and deployment optimization is a plus.

Nice to Have

• Computer Vision (Face Recognition, Liveness Detection)
• Whisper / Speech-to-Text systems
• Stable Diffusion or image generation models
• GraphQL experience
• Kubernetes exposure

Skills

• Python
• LangChain
• FastAPI
• Pinecone
• Docker