Senior AI Engineer - SDE2/SDE3

Role:Senior AI Engineer SDE2/SDE3

Location:Bangalore Bellandur (Outer Ring Road)

Work Model:5 Days (Work from Office)

Experience:510 Years

Reporting To:Head of Engineering

Role Overview

We are looking for aSenior AI Engineerto join a fast-growing technology team and help build cutting-edge AI-powered products in the travel tech space. This role involves designing and deployingproduction-grade AI systems, building intelligent workflows using LLMs, and driving the development of scalable AI infrastructure.

The ideal candidate will have strong backend engineering fundamentals combined with hands-on experience inLLM applications, agentic workflows, and AI system evaluation, and will thrive in afast-paced startup environmentwhere they can take ownership from concept to production.

Key Responsibilities

• Build and ownproduction-grade AI featuresacross the stackfrom prototyping and experimentation to deployment and monitoring
• Design and implementagentic workflowscombining LLM reasoning, retrieval systems, APIs, and business rules
• Build and optimizeRAG-based search systems, including document ingestion, embedding pipelines, vector indexing, hybrid retrieval, and reranking
• Integrate models with internal and external systems usingAPIs, tool calling, and MCP-compatible interfaces
• Drivecontext engineeringby managing instructions, memory, conversation state, and retrieved context to improve model performance
• Developevaluation frameworksincluding benchmark datasets, automated regression tests, and human-in-the-loop review workflows
• Implementobservability and debugging toolsfor AI systems such as trace inspection, latency tracking, hallucination analysis, and failure monitoring
• Establish best practices forAI system reliability, security, guardrails, experimentation, and cost-performance optimization

Must-Have Requirements

• 510 years of software engineering experience, including13 years building and deploying AI/ML or LLM-powered products in production
• Strong programming experience inPython or Java
• Hands-on experience withLLM application patternssuch as RAG, tool/function calling, vector search, reranking, and structured output generation
• Experience designingagent-based workflows and orchestration systems
• Familiarity withModel Context Protocol (MCP)or similar integration frameworks
• Strong understanding ofprompt engineering, context management, and AI system design
• Experience withAI evaluation and observability tools(offline evaluations, monitoring, regression testing, cost/latency tracking)
• Experience usingAI-native developer toolssuch as coding agents or AI-assisted workflows
• Ability to work in afast-paced startup environment with end-to-end ownership

What We Offer

• Opportunity tobuild and scale AI capabilities from the ground up
• Fast iteration cycleswith rapid product releases
• Collaborative engineering culturewith high ownership
• In-person work environmentwith strong team collaboration
• Additional perks and benefits