Artificial Intelligence Engineer

About AiSensy
AiSensy is a WhatsApp-based Marketing & Engagement platform helping businesses drive customer engagement, retention, and revenue growth through WhatsApp.
250,000+ businesses enabled with WhatsApp Engagement & Marketing
800+ crore WhatsApp messages exchanged annually through the AiSensy platform
Trusted by leading brands including Adani, Delhi Transport Corporation, Yakult, Godrej, Aditya Birla Hindalco, Wipro, Asian Paints, India Today Group, Skullcandy, Vivo, PhysicsWallah, Cosco, and more
Businesses drive 25–80% of their revenue through WhatsApp using AiSensy
Mission-driven, high-growth startup backed by Marsshot.vc, Bluelotus.vc, and 50+ angel investors
About the Role
We are looking for a Senior AI Engineer with 4+ years of experience to design, build, and scale production-grade AI systems powering the next generation of AiSensy's WhatsApp engagement platform.
You will work hands-on across LLMs, RAG, AI Agents, embeddings, vector search, AI evaluation, and AI-powered microservices. You will own AI solutions end-to-end—from problem definition and architecture to development, deployment, monitoring, and continuous optimization.
This role is ideal for someone who has moved beyond experimentation and has real-world experience taking AI/ML systems into production, with a strong focus on scalability, accuracy, latency, reliability, and business impact.
What You'll Own
AI/ML & LLM Engineering
Design, develop, and deploy production-grade AI/ML solutions for real-world business use cases.
Build and optimize LLM-powered applications, RAG pipelines, AI Agents, and intelligent automation workflows.
Evaluate and select appropriate models, architectures, prompting strategies, and retrieval approaches for different use cases.
Work with OpenAI, Google Generative AI, and other foundation model providers.
Build reusable AI components and services that can scale across multiple product use cases.
RAG & Vector Search
Design production-grade Retrieval-Augmented Generation (RAG) systems.
Develop effective document ingestion, chunking, embedding, indexing, retrieval, and reranking pipelines.
Work with vector databases such as Pinecone, Qdrant, or equivalent technologies.
Optimize retrieval quality, relevance, latency, and cost.
Implement hybrid search and other advanced retrieval techniques where appropriate.
AI Agents & Automation
Design and build AI Agents capable of reasoning, tool usage, workflow execution, and context management.
Integrate AI systems with internal APIs, databases, and third-party services.
Build reliable guardrails around agentic workflows to ensure accuracy, safety, and predictable behavior.
Develop AI-powered automation for customer engagement and business workflows.
Backend & AI Infrastructure
Build high-performance AI microservices using Python and FastAPI/Flask.
Design scalable APIs and services for AI-powered product features.
Work with MongoDB and other data stores for structured and unstructured AI data.
Design asynchronous and scalable workflows for AI inference and data processing.
Implement caching and optimization strategies using technologies such as Redis where required.
AI Evaluation & Optimization
Establish evaluation frameworks for LLM and RAG applications.
Measure metrics such as accuracy, relevance, groundedness, hallucination rate, latency, and cost.
Develop strategies to reduce hallucinations and improve response quality.
Optimize prompts, retrieval strategies, model selection, and inference workflows.
Continuously evaluate new models and AI technologies for potential production use.
Performance & Reliability
Optimize AI systems for latency, throughput, scalability, reliability, and cost.
Identify performance bottlenecks across model inference, retrieval, APIs, databases, and external integrations.
Design systems capable of handling high-volume production workloads.
Implement appropriate logging, monitoring, error handling, and observability.
Engineering & Technical Leadership
Own AI features from architecture and development through deployment and post-production optimization.
Participate in system design, architecture, and technical decision-making.
Conduct code and design reviews and maintain high engineering standards.
Mentor junior AI/ML engineers and contribute to best practices across the AI engineering team.
Collaborate closely with Product Managers, Backend Engineers, Data teams, and leadership.
Must-Have Qualifications
4+ years of professional experience in AI/ML Engineering, Machine Learning Engineering, Applied AI, or a closely related role.
Strong proficiency in Python and backend development.
Hands-on experience building and deploying production AI/ML systems.
Strong practical experience with LLMs and Generative AI applications.
Hands-on experience building RAG pipelines, including chunking, embeddings, retrieval, and evaluation.
Experience integrating OpenAI SDK, Google Generative AI SDK, or equivalent LLM APIs.
Strong understanding of embeddings, semantic search, vector databases, and retrieval pipelines.
Experience with FastAPI, Flask, or similar Python backend frameworks.
Experience with vector databases such as Pinecone, Qdrant, Weaviate, Milvus, or equivalent.
Experience working with MongoDB or similar databases.
Strong understanding of AI evaluation, hallucination mitigation, prompt engineering, and LLM optimization.
Good understanding of ML fundamentals including Transformers, neural networks, classification, clustering, KNN, and model evaluation.
Understanding of API security, authentication, data privacy, and secure AI application design.
Strong debugging, system design, and problem-solving skills.
Good to Have
Experience with LangChain, LlamaIndex, LangGraph, or similar frameworks.
Hands-on experience building AI Agents / agentic workflows.
Experience with multimodal AI applications.
Exposure to fine-tuning, LoRA/PEFT, or model adaptation workflows.
Experience with hybrid search, reranking, BM25, or advanced retrieval optimization.
Understanding of distributed systems and event-driven architectures.
Experience with Redis or other caching systems.
Experience optimizing LLM inference latency and cost.
Experience with Docker, Kubernetes, AWS, or GCP.
Familiarity with CI/CD and production ML/AI deployment practices.
Experience with Node.js for integrations or auxiliary services.
Experience working on SaaS, MarTech, conversational AI, CRM, CPaaS, or customer engagement products.
What We're Looking For
Someone who has built and shipped AI systems to production, not just worked on POCs.
Strong engineering fundamentals combined with practical AI/ML expertise.
Ability to translate ambiguous business problems into scalable AI solutions.
Strong ownership of system quality, accuracy, performance, and reliability.
Comfortable making technical decisions independently.
Strong experimentation mindset with a focus on measurable outcomes.
Ability to mentor engineers and raise the technical bar of the team.
Comfortable working in a fast-paced, high-growth startup environment.
What Success Looks Like
Production AI features are delivered reliably and adopted by users.
RAG and AI Agent systems achieve strong accuracy and relevance.
AI applications maintain low latency and high reliability at scale.
Hallucination and failure rates are continuously reduced.
AI infrastructure is optimized for performance and cost.
AI capabilities create measurable impact on customer experience and business outcomes.
Engineering standards and AI development practices improve across the team.
Why Join AiSensy?
Build AI products powering customer engagement for 250,000+ businesses.
Work on real-world LLM, RAG, Agentic AI, and conversational AI problems at scale.
Own AI systems from architecture to production.
Work closely with Product, Engineering, and senior leadership.
Join a high-growth, mission-driven SaaS company.
Opportunity to shape AiSensy's next generation of AI-powered products.

Work arrangement
Hybrid