Software Engineer - Applied AI/ML

Overview

About AiSensy

AiSensy is a WhatsApp based Marketing & Engagement platform helping businesses like Skullcandy, Vivo, Rentomojo, Physicswallah, Cosco grow their revenues via WhatsApp.

Enabling 15000+ Businesses with WhatsApp Engagement & Marketing 750mn+ WhatsApp Messages done between Businesses and Users via AiSensy Working with top brands like Skullcandy, Vivo, Rentomojo, Physicswallah & more High Impact as Businesses drive 25-80% Revenues using AiSensy Platform Mission-Driven and Growth Stage Startup backed by Marsshot.vc, Bluelotus.vc & 50+ Angel Investors

What You’ll Do

1. Build and maintain high-performance AI microservices using Python and FastAPI.
2. Develop and optimize Retrieval-Augmented Generation (RAG) systems for production-scale use cases.
3. Integrate AI features using Google Generative AI SDK and OpenAI SDK.
4. Work with vector databases to enable semantic search, embeddings retrieval, and real-time AI workflows.
5. Design and manage scalable data pipelines leveraging MongoDB for storing, indexing, and querying AI-related data.
6. Write clean, reusable, and maintainable code with strong focus on performance, latency, and reliability.
7. Collaborate with product managers, backend engineers, and AI teams to deliver impactful AI-driven features.
8. Participate in design and code reviews to uphold a high-quality engineering culture.

What We’re Looking For

1. Strong proficiency in Python and backend development.
2. Hands-on experience with FastAPI/Flask for building scalable APIs.
3. Solid understanding of RAG, embeddings, chunking strategies, and retrieval pipelines.
4. Experience integrating with Google Gen AI SDK and OpenAI SDK.
5. Fundamental understanding of how Transformers, CNNs, KNN, and other ML algorithms work
6. Familiarity with Vector Databases such as Pinecone, QDrant.
7. Experience with MongoDB for structured/unstructured data handling.
8. Knowledge of AI evaluation, hallucination control, and prompt optimization.
9. Understanding of API security, authentication, and data privacy principles.

Soft Skills

1. Strong problem-solving and experimentation abilities
2. Effective communication and collaboration with cross-functional teams
3. Ownership mindset — you care about product quality, reliability, and accuracy
4. Fast learner who thrives in a fast-paced, high-growth startup environment

Bonus / Good to Have:

1. Experience with LangChain, LlamaIndex, or similar LLM frameworks
2. Familiarity with multimodal models and fine-tuning workflows
3. Exposure to vector search optimization and hybrid retrieval methods
4. Understanding of distributed systems, caching, and LLM latency optimization
5. Basic understanding of CI/CD pipelines, Docker, or AWS for model deployment
6. Experience with Node.js for auxiliary services or integrations
7. Knowledge of Redis or other caching layers for optimizing retrieval and AI response latency