Software Engineer – Generative AI

Location: Delhi with a remote option

Employment type: Full-time

Experience: 0–3 years

Joining: Immediate to [30/45] days

About the role We are looking for a Software Engineer who is excited about building real-world applications using large language models, multimodal AI and generative-AI APIs. This is not a research-only role. You will work on production features that help users generate, edit and improve presentations using AI. You will contribute across AI workflows, backend services, product integrations and evaluation systems. Strong personal projects, internships and open-source work will be considered alongside professional experience.

What you will do

• Build and improve AI workflows using large language models and multimodal models.
• Develop features involving prompt orchestration, structured outputs, document processing and image understanding.
• Integrate AI models from providers such as OpenAI, Anthropic and Google.
• Build systems for generating and modifying presentation content and layouts.
• Improve output quality through evaluations, prompt experimentation and failure analysis.
• Optimize AI workflows for accuracy, latency and cost.
• Develop APIs and services that connect AI models with the AutoPresent product.
• Work with frontend, backend and product teams to take features from concept to production.
• Monitor production behaviour and resolve reliability or quality issues.
• Experiment rapidly and ship improvements based on user feedback.

What we are looking for

• Strong programming ability in Python, TypeScript or JavaScript.
• Good understanding of APIs, databases, data structures and software-development fundamentals.
• Experience building at least one working application using LLM or generative-AI APIs.
• Ability to write clean, maintainable and testable code.
• Comfort working in an early-stage environment with changing requirements.
• Strong problem-solving ability and attention to detail.
• Clear written and verbal communication.

Good to have

• Experience with FastAPI, Node.js, React or Next.js.
• Familiarity with RAG, embeddings, vector databases or agentic workflows.
• Experience processing PDFs, PowerPoint files, images or other business documents.
• Familiarity with cloud platforms, Docker and asynchronous job processing.
• A strong GitHub profile, technical portfolio or deployed product.

What we offer

• Direct ownership of production AI features.
• Exposure to users from consulting, strategy and corporate teams.
• Opportunity to work directly with the founder.
• Remote and flexible working environment.
• Significant learning across AI, product and software engineering.
• Performance-led career progression. Interested candidates should send an email to sarah.jenner@autopresent.ing