AI Engineer

About the job

About the Role: We’re building the next generation of intelligent, autonomous AI systems and are seeking 2–3 experienced AI Engineers to join our product development team. You will play a key role in designing, building, and deploying AI agents and AI assistants that leverage Large Language Models (LLMs) , Retrieval-Augmented Generation (RAG) , and scalable backend systems using Python. Key Responsibilities: • Design, develop, and deploy AI agents powered by cutting-edge LLMs (OpenAI, Anthropic, Mistral, Llama, etc.) • Building end-to-end retrieval-augmented generation (RAG) pipelines from ingestion, chunking, embeddings, and hybrid vector search, ideally using OpenSearch or other leading technologies. • Develop scalable Python microservices and APIs that support AI agent operations and LLM orchestration. • Own data ingestion and storage workflows — manage relational (PostgreSQL) and vector data for efficient retrieval and context management. • Optimize agent reasoning and memory , improving accuracy, contextual continuity, and tool integrations. • Collaborate cross-functionally with PMs, and designers to define and deliver AI-driven product features end-to-end. • Implement monitoring, evaluation, and testing frameworks to measure model quality, latency, and reliability. • Stay ahead of the curve on emerging frameworks and new model capabilities. Required Skills: • Bachelor’s or master’s degree in computer science, Artificial Intelligence, or related field. • Strong hands-on experience building and deploying LLM-powered applications. • Proven experience with AI agents, AI assistants, or conversational systems. • Solid understanding of Retrieval-Augmented Generation (RAG) architectures and search pipelines. • Strong proficiency in Python (FastAPI, Flask, or Django preferred). • Experience with vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus, pgvector, etc.). • Proficient in PostgreSQL and relational schema design. • Familiar with AI agent and LLM orchestration frameworks (LangChain, LlamaIndex, Autogen, CrewAI, etc.). • Experience deploying AI systems to production (cloud, APIs, monitoring, scaling). • Familiar with Docker, Git, and CI / CD workflows. • Proficiency in working with cloud platforms like AWS, Azure, or Google Cloud. • Excellent problem-solving skills and analytical thinking. • Strong communication skills to collaborate with cross-functional teams. • Startup-oriented execution mindset , including : • Strong customer focus and ability to translate user needs into AI-driven solutions. • High level of ownership across the full product lifecycle, from design to deployment. • Ability to iterate quickly , experiment, and adapt in fast-moving environments. • Bias for action with comfort making decisions under uncertainty. Nice to Have: • Experience with agent frameworks (e.g., LangGraph, LangChain, AutoGen, CrewAI). • Familiarity with embedding models, re-ranking, and search relevance tuning. • Experience building internal or customer-facing enterprise search or knowledge assistant products.