Senior Software Engineer – Cortex AI

Jobtailor; Menlo Park (CA); On-site; USD 190,000 - 230,000; Full time

Job summary

Jobtailor is seeking a senior backend architect to architect and scale orchestration engines for complex AI workflows with low latency. You will design high‑performance RAG infrastructure, integrate vector databases, implement automated simulations, and productionize LLM capabilities as multi‑tenant microservices with guardrails and observability.

You will drive infrastructure strategy for model routing, token optimization, and backend support for Snowflake Intelligence and Cortex platforms,

Qualifications

• Bachelor’s degree in Computer Science or a related technical field.
• ],
• job_responsibilities_description:[
• ],
• CoT_job_summary_short::null
• job_summary_short

Responsibilities

• Architect and scale orchestration engines for complex agentic workflows with low-latency tool execution and robust state management.
• Design high-performance RAG infrastructure including vector database integration, search indexing, query processing, result ranking, semantic caching, and automated metadata extraction.
• Develop automated infrastructure for large-scale golden set simulations, error analysis pipelines, and hillclimbing experiments.
• Collaborate with the modeling team to productionize LLM capabilities as hardened, multi-tenant microservices with guardrails and observability.
• Direct infrastructure strategy for model routing, prompt caching, and token optimization.
• Build backend infrastructure powering Snowflake Intelligence, Cortex Agents, and Cortex Search.
• Perform cross-layer debugging across services using logs and telemetry.
• Evaluate customer problems and determine whether they represent bespoke issues or platform gaps worth addressing.

Skills

Distributed Systems

Go Proficiency

Java Proficiency

Python Proficiency

Kubernetes

FoundationDB

Vector Database

Telemetry Logs

Multi-tenant Systems

SQL Engine Internals

Education

Bachelor’s degree in Computer Science

Tools

FoundationDB

Vector Database

Logs Analysis

Telemetry Tools

Job description

• Architect and scale orchestration engines for complex agentic workflows, with low-latency tool execution and robust state management
• Design high-performance RAG infrastructure, including vector database integration, search indexing, query processing, result ranking, semantic caching, and automated metadata extraction
• Develop automated infrastructure for large-scale golden set simulations, error analysis pipelines, and hillclimbing experiments
• Collaborate with the modeling team to productionize LLM capabilities as hardened, multi-tenant microservices with guardrails and observability
• Direct infrastructure strategy for model routing, prompt caching, and token optimization
• Build backend infrastructure powering Snowflake Intelligence, Cortex Agents, and Cortex Search
• Perform cross-layer debugging across services using logs and telemetry
• Evaluate customer problems and determine whether they represent bespoke issues or platform gaps worth addressing

Requirements

• Bachelor’s degree in Computer Science or a related technical field
• 7+ years of experience building distributed systems, high-throughput APIs, or backend infrastructure for AI/ML products
• Deep proficiency in Go or Java and Python
• Strong understanding of database internals, distributed state management, and cloud-native architecture
• Experience with Kubernetes and FoundationDB or similar technologies
• Familiarity with vector indices, agent platforms, and scalable data pipelines
• Experience in a customer-facing technical role
• Product judgment to distinguish bespoke customer problems from platform gaps
• Cross-layer debugging using logs and telemetry
• Experience with eval frameworks for LLM/agent systems, including defining quality metrics and improving quality systematically
• Comfort with ambiguity on open-ended, externally-driven problems
• Bonus experience with query optimization, SQL engine internals, multi-tenant systems handling sensitive enterprise data, and large-scale search infrastructure

Core Competencies

Demonstrates expertise in architecting and scaling orchestration engines and backend infrastructure for AI/ML products, with a strong focus on distributed systems, cloud-native architecture, and cross-layer debugging. Proficient in developing high-performance RAG infrastructure and automated simulations while collaborating effectively with technical teams.

Highest-signal resume keywords

• Distributed Systems Development
• Go, Java, And Python Proficiency
• Kubernetes And FoundationDB Experience
• Cross-Layer Debugging Using Logs And Telemetry
• LLM/Agent Systems Evaluation Frameworks

ATS Optimization Keywords

Hard Skills

• Distributed Systems
• High-Throughput APIs
• Backend Infrastructure
• Database Internals
• Cloud-Native Architecture
• Query Optimization
• SQL Engine Internals
• Error Analysis Pipelines
• Automated Metadata Extraction
• Scalable Data Pipelines

Soft Skills

• Product Judgment
• Comfort With Ambiguity
• Customer-Facing Technical Role

Certifications & Qualifications

• Bachelor’s Degree In Computer Science

Industry Keywords

• AI/ML Products
• Agent Platforms
• Multi-Tenant Systems
• Large-Scale Search Infrastructure

Tools & Technologies

• Kubernetes
• FoundationDB
• Vector Database
• Telemetry Tools
• Logs Analysis