Generative AI Engineer

Job Title : Generative AI Engineer

Relevant Experience : 1-3 years

Location : Bangalore

Job Type : Full-Time on site (5 Days Work From Office)

Company Overview

At Aiqwip, we are building full-stack applications powered by Agentic AI, multimodal agent frameworks, and real-world business logic. We take pride in building highly modular, elegant frontend systems that work seamlessly with intelligent backends to deliver world-class user experiences.

Our focus is on exceptional software design, scalable architectures, and robust AI integrations that turn product visions into reality. With deep experience in analytics, data science, and frontend engineering, our team delivers cutting-edge experiences across enterprise and consumer interfaces.

We’re looking for a generative AI engineer with a builder's mindset, ready to prototype quickly, iterate fast, and deliver results in a fast-paced startup environment.

Responsibilities

Develop, deploy, and maintain end-to-end Generative AI applications.

Architect and implement intelligent agents using agentic frameworks.

Build, debug, and maintain complex systems using industry best practices

Fine-tune LLMs and optimize prompt engineering pipelines.

Work closely with clients, internal teams and clients to gather requirements and deliver solutions

Conduct code reviews, implement version control workflows, and contribute to DevOps pipelines.

Continuously learn and contribute ideas to improve our tech and processes

Stay up-to-date with emerging trends in Generative AI and apply them to solve practical problems.

Experiment with cutting-edge Generative AI technologies.

Must Have Skills

Effective communication and collaboration skills

Proficient in Python and its ecosystem for backend and AI development.

Strong backend engineering using FastAPI or Django.

Understanding of WebSocket communication and event-driven architectures.

Experience working with LLMs and APIs from OpenAI (ChatGPT, GPT-4 / 4o), Azure OpenAI, Anthropic Claude, AWS Bedrock, and Groq.

Familiarity with embedding models like OpenAI, Cohere

Knowledge of LLM observability tools such as LangSmith.

Experience with open-source LLMs like Mistral, LLaMA, Falcon, Mixtral, Yi, or Gemma.

Strong grasp of Agentic AI architectures and hands-on experience with frameworks like LangChain, LangGraph, CrewAI

Expertise in prompt engineering, including prompt chaining, template design (zero-shot, few-shot, chain-of-thought), and system prompts for multi-agent collaboration.

Experience building RAG pipelines with vector databases such as Pinecone, Milvus, ChromaDB, FAISS

Exposure to LLM fine-tuning, LoRA

Proficiency in using Azure AI Services including Azure Document Intelligence and Azure OpenAI Studio.

Working knowledge of Docker, Linux (Ubuntu), and remote development using SSH.

Proficient with API documentation and testing tools such as Swagger / OpenAPI and Postman.

Experience implementing real-world Generative AI use cases such as RAG-based agents, multi-agent Q&A systems, summarization, classification, document parsing, and semantic search.

Strong debugging and problem-solving skills.

Good to Have Skills

Deep understanding of Azure cloud platform is a plus

Ability to build simple frontend interfaces using React.js, HTML, CSS, Tailwind, or Next.js.

Deployment experience using PM2, NGINX with Uvicorn or Gunicorn.