Specialist Technical Support Engineer
Core
Resolve complex P1/P2 incidents and troubleshoot agentic AI workflows, LLM integrations, and cloud/data layers.
Role type
Senior Specialist Technical Support Engineer (Agentic AI & Cloud)
Builds
Production fixes, regression tests, runbooks, and continuous-improvement initiatives for autonomous AI workflows.
Domain
Artificial Intelligence (Agentic AI, LLMs, RAG) + Cloud Infrastructure (AWS, Snowflake)
Deliverable
production ML models
Required skills
Python, SQL, REST APIs, distributed systems, Snowflake, AWS, microservices, event-driven architectures, workflow orchestration, CI/CD, Git, testing frameworks, observability, logging, monitoring, IAM, OAuth 2.0, RBAC, secrets management, agentic AI frameworks (LangGraph, LangChain, PydanticAI, AutoGen, CrewAI, Semantic Kernel), LLM platforms (OpenAI, Azure OpenAI, Anthropic Claude, Amazon Bedrock, Snowflake Cortex, Google Gemini), MCP implementations, RAG architectures, embeddings, vector databases, AI evaluation frameworks, Snowflake Cortex Agents/Search/Analyst/Snowpark, AWS Lambda/ECS/Fargate/Step Functions/EventBridge/SQS/SNS/API Gateway/CloudWatch, Airflow, Temporal, dbt, ServiceNow, Jira Service Management, AI guardrails, governance frameworks.
Preferred skills
None stated.
Technologies
LangGraph, LangChain, PydanticAI, AutoGen, CrewAI, Semantic Kernel, OpenAI, Azure OpenAI, Anthropic Claude, Amazon Bedrock, Snowflake Cortex, Google Gemini, AWS Lambda, ECS, Fargate, Step Functions, EventBridge, SQS, SNS, API Gateway, CloudWatch, Airflow, Temporal, dbt, ServiceNow, Jira.
Responsibilities
Own and resolve complex P1/P2 incidents across agentic AI, cloud, data, and application layers; Troubleshoot AI agent workflows, LLM integrations, RAG pipelines, APIs, MCP tools, and orchestration failures; Analyze Snowflake and AWS environments for performance, security, data, and integration issues; Perform code-level debugging, implement production fixes, and develop regression tests; Monitor system health with observability and LLMOps tools and proactively identify reliability risks; Support automation frameworks, event-driven workflows, and data pipelines; Create runbooks, alerts, knowledge articles, and continuous-improvement initiatives; Collaborate with engineering, architecture, product, and business teams on AI solution adoption; Ensure governance, security, auditability, and safe execution of autonomous AI workflows.
Seniority
Senior, 8–12 years experience, hands-on IC.
