Senior AI Engineer (SDE II - Backend)

Location: Bangalore

Our Journey

Get My Parking (GMP), founded in 2015 in Bengaluru, is on a mission to digitize parking globally and make parking a “sub-conscious experience.” A Great Place to Work-certified startup, GMP operates in over 20 countries, manages 3,000+ parking lots, and has processed over 100 million parking transactions. We bring AI, IoT, and cloud technology together to transform parking infrastructure globally.

What This Role Is About

As an SDE II at GMP, you will design, build, and deploy scalable backend services and AI-powered applications. We are looking for a strong backend engineer with proven Java production experience who has expanded into LLM applications, AI agents, and conversational AI. You will own features end-to-end, turning emerging AI capabilities into reliable, secure, and production-ready products.

What You’ll Do

1. Backend Engineering

Design and maintain scalable backend services and APIs using Java, Spring Boot, Python, and PostgreSQL.

Build reliable microservices, optimize database performance, and design for security, availability, and scale on AWS.

Implement automated testing, monitoring, logging, and alerting for production systems.

2. LLM Applications & AI Agents

Build LLM-powered applications and agents using frontier models and open-weight models.

Implement tool calling, structured outputs, context management, retrieval-augmented generation (RAG), and multi-step agent workflows.

Design reliable AI systems with appropriate validation, retries, fallbacks, and human handoffs.

Evaluate and optimize model quality, latency, cost, and reliability across providers and models.

Build voice-enabled AI applications integrating speech-to-text (STT), text-to-speech (TTS), real-time audio streaming, conversational turn-taking, and interruption handling.

3. Ownership & Collaboration

Translate product requirements into technical solutions and own delivery from design through production monitoring.

Collaborate with product, frontend, and data teams to deliver end-to-end features.

Contribute to code reviews, technical design discussions, and engineering best practices.

What You Must Have

At least 4 years of professional software development experience, including substantial hands-on experience building and maintaining production backend systems in Java.

Strong proficiency in Java, Spring Boot, Hibernate, PostgreSQL, data structures, algorithms, and software design principles.

Experience designing scalable, fault-tolerant services, REST APIs, asynchronous workflows, and distributed systems.

Hands-on experience building LLM-powered applications beyond basic prompt-and-response integrations.

Understanding of model APIs, prompt and context engineering, tool calling, structured outputs, and agent workflow design.

Strong engineering fundamentals, including automated testing, code reviews, CI/CD, debugging, and production troubleshooting.

Nice to have: Voice-enabled AI applications integrating speech-to-text (STT), text-to-speech (TTS)

High degree of ownership of deliverables and ability to gel well with the team

What Will Set You Apart

Experience shipping production AI agents or voice agents, including low-latency interactions and real-time audio processing.

Experience with RAG, embeddings, vector databases, agent evaluation, tracing, and AI observability.

Experience integrating multiple frontier-model providers and deploying or serving open-weight models.

Hands-on AWS and Docker experience, with Kubernetes or model-serving infrastructure being an advantage.

Experience at a high-growth product or SaaS company, or a track record of meaningful open-source contributions and technical projects.