Here's a closer look at this key role:
Design and build AI capabilities for Edwin AI , including incident summarization, alert correlation, anomaly explanation, root-cause analysis assistance, recommendation generation, and guided remediation workflows.
Develop production-grade LLM applications using techniques such as retrieval-augmented generation, tool calling, function calling, prompt orchestration, agentic workflows, structured outputs, and multi-step reasoning pipelines .
Build and optimize RAG pipelines that retrieve relevant observability context from metrics, logs, traces, alerts, topology, incidents, runbooks, knowledge bases, and historical operational data.
Design embedding, indexing, chunking, reranking, query expansion, and semantic retrieval strategies for high-scale observability and AIOps use cases.
Develop AI orchestration services using Python, FastAPI, LangGraph, LangChain, LlamaIndex, or similar frameworks .
Implement structured AI workflows that combine deterministic business logic, statistical methods, retrieval systems, and LLM reasoning.
Collaborate with backend and data engineering teams to define AI-ready data contracts, metadata schemas, context formats, and retrieval APIs.
Build evaluation frameworks for AI quality, including relevance, groundedness, correctness, hallucination reduction, latency, cost, safety, and user usefulness.
Create offline and online evaluation pipelines using golden datasets, synthetic test cases, human review, A/B testing, feedback loops, and production telemetry.
Optimize prompt templates, model selection, retrieval strategies, context windows, latency, token usage, cost, and response consistency.
Implement guardrails for safe and trustworthy AI behavior, including source attribution, citation handling, confidence signals, output validation, policy checks, and fallback strategies.
Work with structured and unstructured observability data to power AI reasoning across events, incidents, alerts, logs, metrics, topology, and service dependencies.
Integrate with commercial and open-source LLMs, embedding models, rerankers, vector databases, and model-serving infrastructure.
Build APIs and services that expose AI capabilities to Edwin’s UI, backend systems, and AIOps workflows.
Instrument AI pipelines with observability, tracing, metrics, structured logs, evaluation signals, and debugging tools.
Partner with SRE and platform teams to monitor production AI behavior, troubleshoot failures, and improve reliability across end-to-end AI workflows.
Collaborate with Product and Design to shape AI UX patterns such as citations, reasoning summaries, confidence indicators, feedback capture, explainability, and human-in-the-loop interactions.
Ensure model inputs, retrieved context, generated outputs, and stored AI artifacts follow data privacy, RBAC, tenant isolation, and compliance requirements.
Participate in technical design discussions, architecture reviews, code reviews, and AI best-practice development.
Mentor engineers on LLM application patterns, RAG design, evaluation methods, and production AI engineering practices.
What You'll Need:
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 programming skills in Python , with experience building production-grade services, APIs, pipelines, or AI applications.
Experience building LLM-powered applications using RAG, embeddings, vector search, prompt engineering, structured outputs, tool calling, or agentic workflows .
Hands-on experience with AI orchestration frameworks such as LangGraph, LangChain, LlamaIndex , or similar technologies.
Experience with model APIs and 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 strategies, embeddings, metadata filtering, reranking, query rewriting, and context assembly.
Experience building evaluation pipelines for LLM applications, including test datasets, human review workflows, automated scoring, and production feedback loops.
Strong software engineering fundamentals, including API design, testing, CI/CD, observability, reliability, and secure coding practices.
Experience working with distributed systems, data pipelines, streaming systems, or large-scale operational data.
Familiarity with vector databases or search systems such as pgvector, OpenSearch, Elasticsearch, Pinecone, Weaviate, Milvus, Qdrant , or similar technologies.
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 handling of customer data.
Ability to collaborate effectively with AI Platform, Backend, Data, SRE, Product, Design, and Engineering teams.
Strong communication skills and the ability to explain AI behavior, quality tradeoffs, and technical implementation details clearly.
Click here to read our International Applicant Privacy Notice.
LogicMonitor is an Equal Opportunity Employer
At LogicMonitor, we believe that innovation thrives when every voice is heard and each individual is empowered to bring their unique perspective. We’re committed to creating a workplace where diversity is celebrated, and all employees feel inspired and supported to contribute their best.
For us, equal opportunity means fostering a truly inclusive culture where everyone has the chance to grow and succeed. We don’t just open doors; we invite you to step through and be part of something bigger. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or status as a protected veteran.
Notice Regarding Use of AI in Hiring
We use artificial intelligence tools to assist with reviewing job applications, such as matching skills and experience to job requirements. These tools support, but do not replace, human review. All hiring decisions are made by our recruiting and hiring teams. You may opt out of AI processing at any time, and your application will still be reviewed. To opt out, please contact us at opt.out@logicmonitor.com .
By submitting your application, you acknowledge this notice.
Our goal is to ensure an accessible and inclusive experience for every candidate.
If you need a reasonable accommodation during the application or interview process under applicable local law, please submit a request via this Accommodation Request Form .
Know your rights: workplace discrimination is illegal. Please click here to review LogicMonitor’s U.S. Pay Transparency Nondiscrimination Provision.