Role overview
As a
**Generative AI Engineer**
, you’ll be a core member of this pod, building and integrating
**agentic systems**
powered by cutting-edge LLM and GenAI technologies. You’ll work closely with Tech Leads and Full Stack Engineers to turn AI capabilities into production-ready enterprise solutions.
**Key Responsibilities**
* Design, develop, and deploy
**agentic AI systems**
leveraging LLMs and modern AI frameworks.
* Integrate
**GenAI models**
into full-stack applications and internal workflows.
* Collaborate on prompt engineering, model fine-tuning, and evaluation of generative outputs.
* Build reusable components and services for
**multi-agent orchestration**
and task automation.
* Optimize AI inference pipelines for scalability, latency, and cost efficiency.
* Participate in architectural discussions, contributing to the pod’s technical roadmap.
**Core Skills & Experience**
**Must Haves**
* 4–8 years of software engineering experience with at least 1–2 years in
**AI/ML or GenAI systems**
in
**production**
* Hands-on experience with
**Python**
only for AI/ML model integration.
* Experience with
**LLM frameworks**
(LangChain, LlamaIndex is a must
* Exposure to
**agentic frameworks**
(Langgraph, AutoGen, CrewAI is a must
* Understanding of
**Git, CI/CD, DevOps**
, and production-grade GenAI deployment practices.
**Nice-to-Have**
* Familiarity with
**Google Cloud Platform (GCP)**
— especially Vertex AI, Cloud Run, and GKE.
* Experience building
**AI APIs, embeddings, vector search**
, and integrating them into applications.
* Experience fine-tuning open-source models (LLaMA, Mistral, etc.) or working with OpenAI APIs.
* Exposure to
**multi-modal AI systems**
(text, image, or voice).
Familiarity with
**Low-Code/No-Code tools**
(e.g., AppSheet) for workflow integration.