Generative AI Platform Engineer

At Pentimenti.Ai, we are on a mission to revolutionise the bid and proposal management industry.

Based in Denmark and now building our core engineering team in Bangalore, we are developing a pioneering enterprise SaaS platform that leverages the power of Generative AI to automate and elevate the entire bid lifecycle.

We are a small, ambitious team solving complex problems, and we're looking for a passionate builder to help us shape the future of our product and the industry.

We are seeking a talented and driven mid-level Backend Software Engineer to join our foundational team in Bangalore.

This is not just a coding role;
you will be a critical part of our AI engine room, responsible for designing, building, and scaling the complex backend systems that power our Retrieval-Augmented Generation (RAG) solutions.

You will tackle challenges in advanced retrieval, context engineering, and long-running asynchronous processing, directly impacting our platform's intelligence and performance.

As an early member of the team, you will have significant ownership and a clear path for growth into a leadership position.

• Design, develop, and maintain robust and scalable backend services using Python and FastAPI.
• Architect and implement production-grade Retrieval-Augmented Generation (RAG) pipelines for our core proposal generation engine.
• Build and manage complex, long-running asynchronous workflows (e.G., multi-document analysis, compliance report generation) using Azure Function Apps, particularly leveraging orchestrators and activity functions (Durable Functions).
• Work extensively with our database stack, including MongoDB for application data and Qdrant for vector search and retrieval.
• Implement and refine techniques in prompt engineering, context engineering, and advanced retrieval to improve the quality and relevance of our AI-generated content.
• Collaborate closely with a small, cross-functional team to define features, solve problems, and deliver high-quality solutions.
• Take full ownership of features from conception to deployment, embodying a product-first mindset to ensure our solutions effectively solve customer problems.

• 3+ years of professional software engineering experience, with a strong focus on backend development.
• 1+ year of hands-on, production-level experience building and deploying applications powered by Generative AI (specifically with RAG architectures).
• Strong proficiency in Python and experience building APIs with frameworks like FastAPI (or Django/Flask).
• Demonstrable, in-depth experience with Azure Function Apps for creating complex, stateful, and asynchronous workflows.
  
  This is a must-have skill.
• Practical experience working with both NoSQL databases (e.G., MongoDB) and vector databases (e.G., Qdrant, Pinecone, Weaviate).
• Experience integrating with third-party LLM APIs (e.G., Azure OpenAI, Google Gemini/PaLM).
• Excellent problem-solving skills and a strong foundation in data structures and system design.
• A strong sense of ownership, adaptability, and a product-first mindset.
  
  You're motivated by seeing your work solve real-world problems.
• Must be based in or willing to relocate to Bangalore.

• Familiarity with AI frameworks like LangChain or LangGraph.
• Experience with building AI agents or multi-agent systems.
• Prior experience working in a fast-paced startup environment.
• An interest in mentoring junior engineers and growing into a technical leadership role.

• Impactful Work: Be a core contributor to a cutting-edge AI product that is transforming an entire industry.
• Deep Tech Challenges: Work on complex and interesting problems at the intersection of AI, data, and enterprise software.
• Growth Opportunity: As an early hire in our Bangalore team, you have an unparalleled opportunity to grow with the company into a leadership role.
• Strong Team Culture: Join a small, dedicated team that values ownership, collaboration, and innovation.
• Competitive Compensation & Benefits.