Software Engineer

Key Responsibilities:

Design and develop Agentic AI architectures that can autonomously plan, reason, and execute tasks.

Implement multi-agent communication protocols for agent-to-agent collaboration and coordination.

Work with Large Language Models (LLMs) such as LLaMA, GPT, etc., for language understanding, generation, and task planning.

Develop and integrate Retrieval-Augmented Generation (RAG) pipelines to enhance the reasoning capability of agents with external knowledge.

Perform fine-tuning of foundational models for specific domains, tasks, or use cases.

Design and experiment with lightweight models (e.g., Phi, Tiny LLMs) for efficiency in real-time or on-device scenarios.

Collaborate cross-functionally with Data Scientists, ML Engineers, and Product Teams to deliver end-to-end AI solutions.

Conduct rigorous testing and evaluation of agent behaviors, decision-making, and performance.

Must-Have Qualifications:

Proven experience in developing and deploying Agentic AI systems.

Strong experience with LLMs, particularly Meta’s LLaMA family or similar open-source models.

Hands-on experience with RAG (Retrieval-Augmented Generation) architectures and related tools like LangChain, Haystack, etc.

Knowledge and experience with model fine-tuning using frameworks like HuggingFace Transformers, PEFT, or LoRA.

Experience in implementing agent-to-agent communication frameworks and multi-agent task handling systems.

Proficiency in Python and AI/ML libraries such as PyTorch, TensorFlow, Transformers, etc.

Familiarity with prompt engineering and chaining logic for LLMs.