Staff Software Engineer, Cloud Infrastructure

Beacon AI•San Carlos, CA
•$224,000 - $260,000•Hybrid

About The Position

Beacon AI is seeking a Staff Software Engineer to lead the buildout of its AWS foundation and LLM platform. The role designs, implements, and operates scalable, reliable, and secure services, with potential focus areas in LLM/ML infrastructure and IoT infrastructure. The engineer works closely with engineering and product management, takes a hands-on approach, and builds from first principles in an environment with ambiguity. The position covers AWS infrastructure and infrastructure-as-code, CI/CD, secure networking, LLM runtime and application services, RAG data systems and vector search, evaluation and observability, safety and privacy controls, data pipelines, IoT deployment infrastructure, application support, and performance optimization. The role owns work from design through production, including on-call and continuous improvement. This is a hybrid role based in San Carlos, California, with at least three days per week onsite and the option to work remotely on remaining days. Due to U.S. export control regulations, candidates must be U.S. Persons, and the company cannot provide visa sponsorship or support visa transfers. All work must be performed in the United States.

Requirements

  • Experience shipping or operating LLM-powered applications in production.
  • Familiarity with RAG design, prompt versioning, and chain orchestration using LangChain or a similar framework.
  • Strong knowledge of core 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, and event-driven patterns using EventBridge and SQS.
  • Applies least privilege, secrets management, network isolation, and compliance practices appropriate to sensitive data.
  • Uses quantitative evaluations, A/B testing, and live metrics to guide improvements.
  • Can explain tradeoffs and align partners across product, security, and application engineering.
  • Hands-on, comfortable with ambiguity, and able to take end-to-end ownership.

Nice To Haves

  • Nine or more years working with serverless or container platforms on AWS.
  • Experience with vector databases, OpenSearch, or pgvector at scale.
  • Hands-on experience with Bedrock Guardrails, Knowledge Bases, or custom policy engines.
  • Familiarity with GPU workloads, Triton Inference Server, or TensorRT-LLM.
  • Experience with big data tools for large-scale processing and search.
  • Background in aviation data or other safety-critical domains.
  • DevOps or DevSecOps experience automating CI/CD for ML and application services.
  • Experience with IoT AWS services or IoT infrastructure.

Responsibilities

  • Design, provision, and maintain AWS infrastructure using infrastructure-as-code tools such as AWS CDK or Terraform.
  • Build CI/CD and testing for applications, infrastructure, and ML pipelines using GitHub Actions, CodeBuild, and CodePipeline.
  • Operate secure networking with VPCs, PrivateLink, and VPC endpoints; manage IAM, KMS, Secrets Manager, and audit logging.
  • Stand up and operate model endpoints using AWS Bedrock and/or SageMaker, and evaluate appropriate compute services for inference jobs.
  • Build and maintain application services that call LLMs through clean APIs, including streaming, batching, and backoff strategies.
  • Implement prompt and tool execution flows with LangChain or similar frameworks, including agent tools and function calling.
  • Design chunking and embedding pipelines for documents, time series, and multimedia, orchestrating them with Step Functions or Airflow.
  • Operate vector search with OpenSearch Serverless, Aurora PostgreSQL with pgvector, or Pinecone, tuning recall, latency, and cost.
  • Build and maintain knowledge bases and data synchronization from S3, Aurora, DynamoDB, and external sources.
  • Create offline and online evaluation harnesses for prompts, retrievers, and chains, tracking quality, latency, and regression risk.
  • Instrument model and application telemetry with CloudWatch and OpenTelemetry; build token-usage and cost dashboards with budgets and alerts.
  • Add guardrails, rate limits, fallbacks, and provider routing to improve resilience.
  • Implement PII detection and redaction, access controls, content filters, and human-in-the-loop review where needed.
  • Use Bedrock Guardrails or policy services to enforce safety standards and maintain audit trails for regulated environments.
  • Build ingestion and processing pipelines for structured, unstructured, and multimedia data; ensure data integrity, lineage, and cataloging with Glue and Lake Formation.
  • Optimize bulk data movement and storage in S3, Glacier, and tiered storage; use Athena for ad-hoc analysis.
  • Manage infrastructure that deploys to and communicates with edge devices, supporting 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, emphasizing uptime and performance.
  • Tune retrieval quality, context-window use, and caching with Redis or Bedrock Knowledge Bases.
  • Optimize inference through model selection, quantization where applicable, GPU/CPU instance choices, and autoscaling strategies.
  • Drive work from design through production, including on-call and continuous improvement.

Benefits

  • 100% of employee medical premiums covered; 25% of dependent medical premiums covered.
  • Three weeks of PTO.
  • 13 or more paid company holidays.
  • 401(k) plan offered; no current employer match.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service