Staff Software Engineer, Cloud Infrastructure

Beacon Venture Capital

. Lead the buildout of Beacon AI’s AWS foundation and LLM platform .

Posted 10/3/2026full-timeSan Carlos • California • United StatesLead💰 $224,000 - $260,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and managing AWS infrastructure, data pipelines, and LLM-powered applications. Proficient in implementing CI/CD processes, secure networking, and compliance practices while optimizing performance and reliability.

Highest-signal resume keywords

AWS Infrastructure ManagementData Pipeline DevelopmentCI/CD ImplementationLLM Application DeploymentLangChain Framework Familiarity

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

AWS CDKPythonInfrastructure as CodeData IngestionData TransformationQuantitative EvaluationsA/B TestingCloud Infrastructure DesignModel Endpoint OperationSecure Networking

Tools & Technologies

AWS BedrockSageMakerOpenSearch ServerlessAurora PostgreSQLGlueLake FormationS3AthenaEventBridgeSQS

Industry Keywords

Compliance PracticesLeast PrivilegeSecrets ManagementNetwork IsolationCloud ServicesMachine LearningData SynchronizationTelemetryAudit LoggingEdge Device Communication

Tech Stack

Tools & technologies

AWSCloudDynamoDBPostgresPython

About the role

Key responsibilities & impact

Lead the buildout of Beacon AI’s AWS foundation and LLM platform
Design, provision, maintain, and operate scalable, reliable, and secure AWS infrastructure
Build CI/CD and testing for applications, infrastructure, and ML pipelines
Manage secure networking, IAM, KMS, Secrets Manager, and audit logging
Operate model endpoints using AWS Bedrock and/or SageMaker
Build application services that call LLMs through APIs with streaming, batching, and backoff strategies
Implement prompt and tool execution flows with LangChain or similar frameworks
Design chunking, embedding, ingestion, and processing pipelines for structured, unstructured, time-series, and multimedia data
Operate vector search using OpenSearch Serverless, Aurora PostgreSQL with pgvector, or Pinecone
Build and maintain knowledge bases and data synchronization from S3, Aurora, DynamoDB, and external sources
Create evaluation harnesses and track quality, latency, regression risk, telemetry, token usage, and costs
Implement guardrails, rate limits, fallbacks, provider routing, PII detection, redaction, access controls, content filters, and audit trails
Build data pipelines using Glue, Lake Formation, S3, Glacier, Athena, and related services
Manage infrastructure communicating with edge devices, including secure messaging, identity, and over-the-air updates
Partner with product and application teams to integrate retrieval services, embeddings, and LLM chains into user-facing features
Provide expert troubleshooting for cloud and ML services
Optimize retrieval quality, context-window usage, caching, inference, model selection, hardware choices, and autoscaling
Own work from design through production, including on-call and continuous improvement

Requirements

What you’ll need

At least 8 years of professional work experience, or a master’s with 5 years of experience related to the role
Experience building and managing data pipelines
Experience designing, setting up, and maintaining cloud infrastructure using Infrastructure as Code tools such as AWS CDK
Experience building robust CI/CD and testing components
Production experience shipping or operating LLM-powered applications
Familiarity with RAG design, prompt versioning, and chain orchestration using LangChain or similar
Strong knowledge of AWS services including VPC, IAM, KMS, CloudWatch, S3, ECS/EKS, Lambda, Step Functions, Bedrock, and SageMaker
Experience building ingestion and transformation pipelines in Python
Familiarity with Glue, Athena, EventBridge, and SQS
Knowledge of least privilege, secrets management, network isolation, and compliance practices
Experience using quantitative evaluations, A/B testing, and live metrics
Must be a U.S. Person
Must be authorized to work lawfully in the United States
Must not require employment visa sponsorship or visa transfer
Willingness to work in the San Francisco Bay Area / relocate if necessary
Ability to work onsite in San Carlos, California at least 3 days per week

Benefits

Comp & perks

100% of employee medical premiums covered; 25% for dependents
3 weeks PTO
13+ paid company holidays
401(k) offered
Equity offered
Remote work on remaining days in a hybrid schedule