Artificial Intelligence Engineer

Atologist Infotech is seeking an experienced and forward-thinking AI Engineer to contribute to the shaping and scaling of the AI Agent Framework. In this hands-on engineering position, your primary focus will be on the development of intelligent and modular agent systems capable of reasoning, planning, and autonomously interacting in real-world scenarios. Working closely with a collaborative team, you will be responsible for designing and implementing agent-oriented systems that facilitate task decomposition, memory management, and contextual planning. Additionally, you will play a key role in extending the in-house AI Agent Framework by incorporating reusable components such as tools, memory modules, and orchestration logic. Your duties will also involve building and integrating vector search, semantic retrieval, and memory systems to empower long-term, goal-oriented behavior in agents. You will be tasked with connecting LLMs (e.g., OpenAI, Anthropic) and NLU/NLP layers to enable natural task inputs and autonomous reasoning capabilities. Furthermore, you will develop RESTful APIs using FastAPI, Flask, or Django to expose agent functionalities and facilitate integration with other products. As an AI Engineer at Atologist Infotech, you will be expected to design scalable, event-driven microservice architectures customized for AI-native workloads and agent frameworks. Emphasizing responsible AI design, you will prioritize user safety, transparency, and privacy throughout the development process. **Key Responsibilities:** - AI Agent System Development: Design and implement agent-oriented systems supporting task decomposition, memory handling, and contextual planning. - Framework Engineering: Extend the in-house AI Agent Framework with reusable components like tools, memory modules, and orchestration logic. - Contextual Intelligence: Build and integrate vector search, semantic retrieval, and memory systems to enable long-term, goal-driven agent behavior. - Natural Language Interfaces: Connect LLMs and NLU/NLP layers for natural task inputs and autonomous reasoning capabilities. - API Engineering: Develop RESTful APIs using FastAPI, Flask, or Django to expose agent capabilities and integrate with other products. - System Architecture: Design scalable, event-driven microservice architectures tailored for AI-native workloads and agent frameworks. - Ethical AI: Prioritize responsible AI design with user safety, transparency, and privacy at the core. **Required Skills & Qualifications:** - Education: Bachelors or Masters degree in Computer Science, Artificial Intelligence, or a related field. - Python Proficiency: Strong software engineering skills in Python (3.x) with expertise in async programming, architecture design, and typing. - AI/LLM Experience: Practical experience using LLMs for reasoning, prompt engineering, chaining, or building agent-like applications. - Frameworks & Tools: FastAPI, Flask, or Django; LangChain, LlamaIndex, or other agent frameworks; Vector stores (FAISS, Weaviate, Pinecone); PostgreSQL, Redis, and event queues (Celery, RabbitMQ). - Version Control & Testing: Proficient with Git workflows and writing tests using Pytest or similar. **Bonus Skills (Nice-to-Have):** - Experience with autonomous agents, tool-calling, or memory-driven task systems. - Familiarity with cognitive architectures or symbolic reasoning. - Contributions to open-source AI frameworks or tooling. This is a full-time, permanent position offering benefits such as leave encashment, paid sick time, paid time off, and Provident Fund. The work schedule is fixed from Monday to Friday. Experience: AI - 3 years (Preferred) Work Location: In person,