Senior AI Engineer
LogicMonitor3 hours ago
Bengaluru, IndiaSenior / Staff+
Responsibilities
- Design and build Edwin AI capabilities for incident summarization, alert correlation, anomaly explanation, root-cause assistance, recommendations, and guided remediation.
- Develop production-grade LLM applications using retrieval-augmented generation, tool and function calling, prompt orchestration, agentic workflows, structured outputs, and multi-step reasoning.
- Build retrieval pipelines using observability data such as metrics, logs, traces, alerts, topology, incidents, runbooks, and historical operational data.
- Develop AI orchestration services, APIs, evaluation pipelines, guardrails, and production monitoring for AI quality, reliability, safety, latency, cost, and usefulness.
- Optimize prompts, model selection, retrieval strategies, context usage, response consistency, and AI workflow performance.
- Collaborate with backend, data, platform, SRE, product, and design teams on data contracts, AI UX, architecture, reliability, privacy, RBAC, tenant isolation, and compliance.
- Mentor engineers on LLM application patterns, RAG design, evaluation methods, and production AI engineering practices.
Requirements
- Bachelor’s degree in Computer Science, Machine Learning, Data Science, Software Engineering, or a related technical field, or equivalent practical experience.
- 5–8+ years of experience in software engineering, machine learning engineering, AI engineering, data engineering, or backend systems.
- Strong Python programming skills and experience building production services, APIs, pipelines, or AI applications.
- Experience building LLM-powered applications with RAG, embeddings, vector search, prompt engineering, structured outputs, tool calling, or agentic workflows.
- Hands-on experience with LangGraph, LangChain, LlamaIndex, or similar AI orchestration frameworks.
- Experience with model APIs or platforms such as OpenAI, Azure OpenAI, Anthropic, AWS Bedrock, Google Vertex AI, or open-source model-serving stacks.
- Strong understanding of retrieval systems, semantic search, chunking, embeddings, metadata filtering, reranking, query rewriting, and context assembly.
- Experience building LLM evaluation pipelines with test datasets, human review, automated scoring, and production feedback loops.
- Strong software engineering fundamentals including API design, testing, CI/CD, observability, reliability, and secure coding.
- Experience with distributed systems, data pipelines, streaming systems, or large-scale operational data.
- Familiarity with pgvector, OpenSearch, Elasticsearch, Pinecone, Weaviate, Milvus, Qdrant, or similar vector databases and search systems.
- Experience with containers, Kubernetes, cloud-native deployment, and production service operations.
- Understanding of AI safety, data privacy, RBAC, tenant isolation, prompt injection risks, grounding, hallucination mitigation, and secure customer-data handling.
- Strong collaboration and communication skills, including the ability to explain AI behavior, quality tradeoffs, and technical implementation details.
Tech Stack
Categories
About LogicMonitor
LogicMonitor provides an AI-first observability and IT infrastructure monitoring platform delivered as SaaS for enterprises and managed service providers. It unifies monitoring across data centers and public clouds (AWS, Azure, GCP), networks, servers, databases, virtualization, and logs, with alerting, dashboards, and incident workflows sold by subscription. Founded in 2007 and headquartered in Santa Barbara, California, LogicMonitor is privately held and owned by Vista Equity Partners.