Company Description

We’re looking for a Machine Learning Engineer to join our team! 
If you're excited about applied AI, agentic systems, and want to build intelligent tools that truly collaborate with people — we’d love to welcome you on board. Join us and help shape the future of AI-powered workplace assistants. 

We are developing an AI-powered internal assistant framework that enables intelligent, context-aware interactions across organizational environments. The system is designed to enhance how users access, understand, and act on complex project information by leveraging semantic search, agentic AI, LLM/LMM models, and MCP (Multi-Context Protocol).  

This assistant framework will serve as a foundation for building task-specific agents capable of integrating with various enterprise tools and knowledge sources. It is aimed at supporting day-to-day operations, minimizing cognitive overload, and improving information retrieval across technical and management roles, by unifying fragmented knowledge and workflows into a seamless, AI-driven interface. We're building a system that doesn't just respond — it understands, adapts, and collaborates. 

Job Description

• Develop and integrate ML and NLP models to power intelligent assistant features 

• Build agentic workflows using LangChain, LangGraph, or similar frameworks 

• Prototype user interfaces and internal tools using Streamlit or Gradio 

• Collaborate with the engineering and product teams to plan and deliver ML-driven features 

• Work with Docker to manage development and runtime environments 

• Use Git for version control and write clean, maintainable code 

• Query structured data using SQL 

• Contribute to model deployment and operations in a cloud environment (primarily Azure)

Qualifications

• 3+ years of experience in a similar position 

• Proficient in Python, with experience in building data pipelines and interacting with APIs 

• Experience with agentic AI frameworks such as LangChain or LangGraph 

• Solid understanding of machine learning and NLP, especially transformer-based architectures (e.g., BERT, GPT), embeddings, and their use in tasks such as retrieval-augmented generation (RAG), semantic search, and classification 

• Hands-on experience with ML frameworks (e.g., PyTorch, TensorFlow) 

• Familiarity with prototyping tools such as Streamlit or Gradio 

• Experience of engineering best practices: Git, Docker, cloud basics, and task estimation 

• Working knowledge of SQL 

• Upper-Intermediate level of English (both written and spoken) 

WOULD BE A PLUS 

• Experience with other agentic or LLM orchestration tools 

• Experience with MLOps or model deployment 

• Comfortable working in Linux terminal environments