Description

You will design, build, and deploy agentic AI systems and LLM-powered applications.

This role is on-site.

Responsibilities

• Develop and deploy agentic AI systems using LLMs and modern frameworks.
• Integrate GenAI models into full-stack applications and internal workflows.
• Collaborate on prompt engineering, model fine-tuning, and evaluation.
• Build reusable components for multi-agent orchestration and task automation.
• Optimize AI inference pipelines for scalability, latency, and cost efficiency.

Required Skills

• 4–8 years of software engineering experience, with 1–2 years in AI/ML or GenAI production.
• Hands-on Python experience for AI/ML model integration.
• Experience with LLM frameworks (LangChain, LlamaIndex required).
• Exposure to agentic frameworks (Langgraph, AutoGen, CrewAI required).
• Understanding of Git, CI/CD, DevOps, and production-grade GenAI deployment.
• Experience building AI APIs, embeddings, and vector search integration.
• Experience fine-tuning open-source models (LLaMA, Mistral) or using OpenAI APIs.

Preferred Skills

• Familiarity with Google Cloud Platform (Vertex AI, Cloud Run, GKE).
• Exposure to multi-modal AI systems (text, image, or voice).

Key Skills

Education

Any Graduate