AI Engineer

Role Overview
We are looking for a hands-on AI Engineer to lead the development of our next-generation conversational and agentic platforms. You won’t just be writing prompts; you will be architecting complex, multi-agent workflows and robust RAG pipelines that bridge the gap between Large Language Models and real-world business utility. The ideal candidate is a Python expert who thinks in terms of system reliability, state management, and seamless integrations.

Key Responsibilities

• Agentic Systems Design: Architect and optimize LLM-powered systems using multi-agent frameworks to handle complex, non-linear tasks.

• RAG Pipeline Engineering: Build and refine Retrieval-Augmented Generation (RAG) systems, focusing on advanced chunking, metadata filtering, and re-ranking to minimize hallucinations.

• AI Integration & API Development: Develop high-performance APIs (Fast API/Flask) to integrate AI capabilities into our existing CRMs and external ecosystems.

• State Management: Utilize frameworks like LangGraph to manage conversational state and cyclic loops in agentic workflows.

• Evaluation & Guardrails: Implement robust monitoring and guardrails (e.g., NeMo, Pydantic, or custom validators) to ensure output quality, safety, and reliability.

• Infrastructure: Manage and optimize Vector Databases (Pinecone, Weaviate, Milvus) for high-speed, relevant context retrieval.

• Core Programming: Mastery of Python and asynchronous programming patterns.

• AI Frameworks: Deep experience with LangChain and/or LangGraph (specifically for agentic behaviour).

• LLM Proficiency: Hands-on experience with OpenAI (GPT-4), Claude, and Open Source models (Llama 3, Mixtral).

• Data & Search: Strong understanding of Vector DBs, embedding models, and hybrid search techniques.

• Software Engineering: Proficiency in Git, Docker, and CI/CD pipelines for AI deployment.

• Database Knowledge: Experience with SQL and NoSQL databases to support CRM integrations.