Senior Artificial Intelligence Engineer

Description

Job Summary: We are seeking an AI engineer to lead the creation of intelligent agents, experimenting with and deploying autonomous solutions into production with full autonomy. Key Highlights: 1. Autonomy to choose AI models and architectures. 2. Develop autonomous agents using LangChain, Agno, and market-available LLMs. 3. Provide technical leadership, mentor junior engineers, and elevate the team's engineering standards. You don’t just want to use AI—you want to build what comes next. We’re expanding our frontier of Artificial Intelligence and looking for an engineer who will proactively lead the development of intelligent agents that deliver real value—not proof\-of\-concepts left in a drawer. Here, you’ll have genuine autonomy: choose the model, propose the architecture, experiment, validate, and deploy to production—with support, not micromanagement. What you’ll do: \- Design and develop autonomous agents using LangChain, Agno, and other modern frameworks, integrating multiple tools into intelligent workflows. \- Build conversational agents with short- and long-term memory, ensuring traceability and personalization. \- Evaluate and integrate market-available LLMs—OpenAI, Gemini, DeepSeek, Cohere—with critical awareness of trade\-offs between performance and cost. \- Structure RAG pipelines with vector databases (ChromaDB, FAISS) connected to corporate data in Snowflake. \- Build knowledge extraction mechanisms via web scraping (Crawl4AI) and document parsing (Docling). \- Integrate agents with APIs so they perform real actions in systems—not just answer questions. \- Provide technical leadership, mentor junior engineers, and elevate the team's engineering standards. \- Translate business needs into practical solutions in collaboration with internal teams. Requirements Solid Python skills with Transformers, LangChain/LlamaIndex/Agno. Proven experience building and deploying autonomous agents and LLMs in production. Experience with RAG, vector databases (ChromaDB, FAISS), and semantic search. API integrations (FastAPI, requests) and database experience (Snowflake preferred). Engineering best practices: GitHub, clean code, scalable solutions. Degree in Engineering, Computer Science, Statistics, or related field. Desirable Experience with MLOps and the full model lifecycle in production. Knowledge of LLM fine\-tuning or quantization. AI-powered conversational projects integrated with WhatsApp. Background in classical Machine Learning (supervised, unsupervised, RL). Prior role as a technical reference in multidisciplinary teams. Other Information No portfolio submission is required; however, if you have relevant projects on GitHub, feel free to include the link in your resume.