Sr Engineer - Ad Tech

Overview

Senior individual contributor role on Target's AI Platform team, building production-grade AI capabilities (LLM applications, RAG, AI agents, MCP) and distributed backend systems, and helping shape the platform's technical direction.

What you'll do

• Build and integrate production-grade applications using large language models, including prompt engineering, model integration, structured outputs, and inference workflows.
• Design and implement Retrieval-Augmented Generation solutions covering retrieval, embeddings, metadata filtering, reranking, grounding, citations, and evaluation.
• Build agentic workflows using agent frameworks and tool-enabled architectures, including Model Context Protocol (MCP) and multi-step agent interactions.
• Design reliable patterns for agent, tool, and service interactions with clear separation of responsibilities and measurable execution behavior.
• Build approaches to evaluate AI systems for correctness, reliability, grounding, tool usage, and regression across model and prompt changes.
• Design scalable, resilient distributed systems that support AI workloads and high-volume production use cases.
• Build backend services using Java or Kotlin, Spring Boot, microservices, APIs, and cloud-native patterns.
• Drive design decisions for core platform components, balancing performance, scalability, maintainability, and operational requirements.
• Raise engineering standards through thoughtful code reviews, design reviews, mentoring, and strong implementation practices.
• Investigate and resolve complex issues across distributed services, AI workflows, performance, latency, and production reliability.
• Build AI systems that are resilient, fault-tolerant, and suitable for production workloads.
• Design monitoring, logging, tracing, metrics, and operational signals that make AI applications measurable and diagnosable.
• Identify and improve latency, throughput, resource utilization, and model/tool execution efficiency.
• Participate in production readiness, incident analysis, reliability improvements, and engineering practices that reduce operational toil.

What you'll need

• 4-year degree in Computer Science, Engineering, or equivalent practical experience.
• 4–7 years of software engineering experience, with meaningful experience as a senior individual contributor.
• Hands-on experience building and shipping LLM-powered or agentic applications into production.
• Strong experience with LLM integration, prompt engineering, structured outputs, and production AI application patterns.
• Practical experience building RAG systems, including retrieval, embeddings, metadata filtering, reranking, grounding, and evaluation.
• Experience with AI agent frameworks, tool calling, agent orchestration, MCP, or similar agentic architectures.
• Strong proficiency in Java/Kotlin and Spring Boot, with experience building APIs and distributed services.
• Strong understanding of microservices, asynchronous systems, APIs, resilience, scalability, and failure handling.
• Hands-on experience building production systems with monitoring, logging, metrics, alerting, and operational readiness.
• Experience with cloud-native environments and technologies such as Kubernetes, Docker, CI/CD, and managed cloud services.
• Strong coding, debugging, design, testing, code review, and problem-solving skills.

Nice to have

• Experience building multi-agent systems or agent-to-agent architectures.
• Experience with Model Context Protocol (MCP) or similar tool/context integration patterns.
• Experience with vector databases, embedding systems, reranking, or modern retrieval infrastructure.
• Experience designing AI evaluation frameworks, including deterministic evaluation, LLM-based evaluation, and production regression testing.
• Experience with observability platforms and distributed tracing for AI or microservice workloads.
• Experience working with Kafka, Redis, or other distributed infrastructure technologies.
• Experience building internal platforms or reusable AI capabilities consumed by multiple engineering teams.
• Strong understanding of AI system reliability, security, governance, and responsible engineering practices.

Details

• Location: Bangalore, India.