Data Scientist - Agentic AI

We are seeking a Data Scientist – Agentic AI to build and operationalize core agentic workflows that power Marvis, Juniper's next-generation AI assistant for network operations. The successful candidate will work at the intersection of data science, generative AI, and production engineering to design, implement, and evaluate reasoning pipelines, tool-calling patterns, skills, and MCP server integrations. The ideal candidate will combine practical experience with LLM-based agentic frameworks (LangGraph preferred) and software engineering discipline to deliver reliable, observable AI systems in a cloud-native environment.

Responsibilities:

• Design, implement, and iterate on agentic workflows using LangGraph, including ReACT orchestration loops, dynamic tool selection and binding, multi-step reasoning, and self-correction patterns.
• Develop and maintain MCP (Model Context Protocol) servers and skills , defining tool schemas, implementing domain-specific tools, writing skill playbooks (SKILL.md), and managing server lifecycle (versioning, deployment, monitoring).
• Integrate and optimize LLM capabilities at production scale, including structured outputs, streaming, function/tool calls, prompt engineering, and robust error handling across agent execution paths.
• Build and refine retrieval and memory services for agentic systems, including RAG pipelines, vector-store-backed semantic search, hybrid retrieval, long-term agent memory (semantic, episodic, procedural), and relevance tuning.
• Design and execute evaluation frameworks for non-deterministic agentic systems , defining metrics, building test harnesses, running A/B tests on skills and tool configurations, and driving continuous quality improvement.
• Collaborate with domain experts (network engineers, product managers) to formalize networking problems as agentic workflows, translating troubleshooting playbooks into skills, tools, and data pipelines.
• Develop data analysis and transformation logic that runs in sandboxed execution environments (Code Mode), including multi-tool orchestration scripts, data aggregation, and visualization.
• Deploy and operate containerized services in Kubernetes, contributing to CI/CD pipelines, container image management, health probes, and resource optimization.
• Own observability for agentic workflows , implementing tracing, logging, cost tracking, and performance monitoring to ensure reliability of non-deterministic systems in production.

Education and Experience Required:

• Bachelor’s, Master's or PhD degree in computer science, data science, mathematics, statistics, or a closely related quantitative discipline.
• Typically, 4-7 years of experience building production ML/AI systems, with at least a year of hands-on work with generative AI and LLM-based applications.

Knowledge and Skills:

• Production experience with agentic orchestration frameworks: LangGraph (strongly preferred), LangChain, Claude Agent SDK, or equivalent , beyond prototypes.
• Solid understanding of agentic design patterns: ReACT loops, tool/function calling, dynamic tool binding, skill-based execution, multi-step planning, and self-correction.
• Hands-on experience with MCP (Model Context Protocol) or equivalent tool-serving protocols: tool schema design, server implementation, registry management.
• LLM API integration at scale: prompt engineering, structured outputs, streaming, error handling, and cost optimization.
• RAG pipeline design: chunking strategies, re-ranking, hybrid search, vector stores (OpenSearch or equivalent), and relevance optimization.
• Experience building evaluation and testing frameworks for non-deterministic AI systems (offline evals, A/B testing, LLM-as-judge).
• Strong foundation in statistical and machine learning techniques , anomaly detection, time-series analysis, clustering, causal inference, or related methods.
• Applied ML intuition: knowing when to use retrieval vs. fine-tuning, prompt engineering vs. structured generation, and how to debug model behavior in production.
• Proficient Python developer with experience in production codebases (not just notebooks).
• Kubernetes: deploying, scaling, and managing workloads (Deployments, Services, ConfigMaps, Secrets, health probes).
• CI/CD pipelines for automated build, test, and deploy (Jenkins, GitHub Actions, ArgoCD, or similar).
• Container image management: building, tagging, versioning via Docker; familiarity with a container registry (ECR, GCR).
• Backend service development: FastAPI or equivalent; REST/GraphQL API design.
• Observability for AI systems: experience with tracing, monitoring, and logging tools (LangFuse, Prometheus, or equivalent).

Benefits:

• Comprehensive suite of benefits supporting physical, financial, and emotional wellbeing.
• Investment in career development and growth.
• Unconditional inclusion and celebration of individual uniqueness.