Software Engineer - AI Products at ixigo

New Delhi, delhi, India -

Full Time

Start Date

Immediate

Expiry Date

20 Aug, 26

Salary

0.0

Posted On

22 May, 26

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Python, LLMs, Prompt Engineering, RAG, Agentic AI, System Design, Backend Engineering, Conversational AI, Real-time Systems, Vector Databases, Docker, Kubernetes, WebSockets, Redis, PostgreSQL, Node.js

Industry

technology;Information and Internet

Description

Company Description About ixigo Launched in 2007 by Aloke Bajpai & Rajnish Kumar, ixigo (Le Travenues Technology Limited) is a technology company focused on empowering Indian travellers to plan, book and manage their trips across rail, air, buses and hotels. ixigo assists travellers in making smarter travel decisions by leveraging artificial intelligence. The ixigo, ConfirmTkt and AbhiBus apps allow travellers to book train tickets, flight tickets, bus tickets, hotels, and cabs, and provide travel utility tools and services developed using in-house proprietary algorithms and crowd-sourced information. With over 54 crore Annual Active Users in Fiscal 2025, ixigo is the leading OTA for Next Billion Users in India. For more information, please visit http://www.ixigo.com What You’ll Do Design and build backend systems that power real-time, low-latency AI experiences Architect and implement agentic AI flows: tool calling, multi-step reasoning, orchestration, memory, and planning Build and evolve conversational AI systems: dialogue management, context handling, intent routing, fallback design Own the infra behind AI features: streaming responses, WebSocket/SSE pipelines, queue-based orchestration Make product-level decisions: you’ll have opinions on what to build, not just how to build it Work on voice-enabled systems (STT/TTS, streaming APIs) as part of end-user experiences Deploy and operate services with a focus on low latency, high availability, and robustness Instrument, monitor, and improve AI systems in production (eval frameworks, latency tracking, cost optimization) What We’re Looking For Must Have: 1- 4 years of backend and AI engineering experience. Strong proficiency in Python Hands-on experience building with LLMs: prompt engineering, function/tool calling, RAG, embeddings, fine-tuning awareness Experience with agentic AI patterns: multi-agent orchestration, ReAct loops, planner-executor architectures, or similar Strong fundamentals in real-time systems Keen interest in building AI-driven products, particularly voice and conversational experiences Strong systems design instincts, with a practical mindset for navigating technical tradeoffs Product thinking: you understand why you’re building something, not just the ticket description Comfort with ambiguity: AI product development is fast, iterative, and occasionally chaotic Strong Signals Built or shipped AI products (voice or text chatbots, copilots, assistants) Experience designing evaluation and feedback loops for AI systems Contributed to or built open source developer tools, SDKs, or internal platforms Bonus Experience with voice AI / speech-to-text / text-to-speech pipelines Background in distributed systems, message queues (Kafka, RabbitMQ, Redis Streams) Exposure to on-device or edge AI inference Open-source contributions in the AI/ML space Tech You’ll Likely Touch LLMs (OpenAI, Anthropic, open-source models), Python/Node.js, Redis, PostgreSQL, WebSockets / SSE, Docker, Kubernetes, vector databases, CI/CD pipelines, observability tools. What We Value Ownership — you see a problem, you fix it. You don’t wait for a spec. Speed with taste — ship fast, but ship something you’d want to use yourself. Clear thinking — you can explain a complex system in simple terms. Curiosity — the AI landscape moves weekly. You keep up because you want to, not because you have to. Job Description What You’ll Do Design and build backend systems that power real-time, low-latency AI experiences Architect and implement agentic AI flows: tool calling, multi-step reasoning, orchestration, memory, and planning Build and evolve conversational AI systems: dialogue management, context handling, intent routing, fallback design Own the infra behind AI features: streaming responses, WebSocket/SSE pipelines, queue-based orchestration Make product-level decisions: you’ll have opinions on what to build, not just how to build it Work on voice-enabled systems (STT/TTS, streaming APIs) as part of end-user experiences Deploy and operate services with a focus on low latency, high availability, and robustness Instrument, monitor, and improve AI systems in production (eval frameworks, latency tracking, cost optimization) Qualifications What We’re Looking For Must Have: 1- 4 years of backend and AI engineering experience. Strong proficiency in Python Hands-on experience building with LLMs: prompt engineering, function/tool calling, RAG, embeddings, fine-tuning awareness Experience with agentic AI patterns: multi-agent orchestration, ReAct loops, planner-executor architectures, or similar Strong fundamentals in real-time systems Keen interest in building AI-driven products, particularly voice and conversational experiences Strong systems design instincts, with a practical mindset for navigating technical tradeoffs Product thinking: you understand why you’re building something, not just the ticket description Comfort with ambiguity: AI product development is fast, iterative, and occasionally chaotic Strong Signals Built or shipped AI products (voice or text chatbots, copilots, assistants) Experience designing evaluation and feedback loops for AI systems Contributed to or built open source developer tools, SDKs, or internal platforms Bonus Experience with voice AI / speech-to-text / text-to-speech pipelines Background in distributed systems, message queues (Kafka, RabbitMQ, Redis Streams) Exposure to on-device or edge AI inference Open-source contributions in the AI/ML space Tech You’ll Likely Touch LLMs (OpenAI, Anthropic, open-source models), Python/Node.js, Redis, PostgreSQL, WebSockets / SSE, Docker, Kubernetes, vector databases, CI/CD pipelines, observability tools. What We Value Ownership — you see a problem, you fix it. You don’t wait for a spec. Speed with taste — ship fast, but ship something you’d want to use yourself. Clear thinking — you can explain a complex system in simple terms. Curiosity — the AI landscape moves weekly. You keep up because you want to, not because you have to. Additional Information Candidates are responsible for safeguarding sensitive company data against unauthorized access, use, or disclosure, and for reporting any suspected security incidents in line with the organization's ISMS (Information Security Management System) policies and procedures.

Responsibilities

Design and build backend systems for real-time, low-latency AI experiences, including agentic AI flows and conversational systems. Own the infrastructure for AI features and optimize production systems for latency and cost.