SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Beacon AI is building an AI platform to make flying safer, more efficient, and more capable. The company is backed by top investors, has secured a dozen Department of Defense contracts, and partners with major airlines to deliver mission-critical systems.
You will design, implement, and operate cloud infrastructure and LLM platform services that are scalable, reliable, and secure. This role spans multiple areas: AWS foundation buildout, LLM/ML infrastructure, IoT infrastructure, and data pipeline construction.
Key responsibilities include:
- Cloud Infrastructure: Design and provision AWS infrastructure using IaC tools (AWS CDK, Terraform). Build CI/CD pipelines with GitHub Actions, CodeBuild, and CodePipeline. Operate secure networking with VPCs, PrivateLink, VPC endpoints, IAM, KMS, Secrets Manager, and audit logging.
- LLM Platform and Runtime: Stand up and operate model endpoints using AWS Bedrock and/or SageMaker. Evaluate when to use ECS/EKS, Lambda, or Batch for inference jobs. Build application services that call LLMs through clean APIs with streaming, batching, and backoff strategies. Implement prompt and tool execution flows with LangChain or similar.
- RAG Data Systems: Design chunking and embedding pipelines for documents, time series, and multimedia. Orchestrate with Step Functions or Airflow. Operate vector search using OpenSearch Serverless, Aurora PostgreSQL with pgvector, or Pinecone. Build and maintain knowledge bases with data syncs from S3, Aurora, DynamoDB, and external sources.
- Evaluation and Observability: Create offline and online eval harnesses for prompts, retrievers, and chains. Instrument telemetry with CloudWatch and OpenTelemetry. Build token usage and cost dashboards with budgets and alerts.
- Safety and Compliance: Implement PII detection and redaction, access controls, content filters, and human-in-the-loop review. Use Bedrock Guardrails or policy services. Maintain audit trails for regulated environments.
- Data Pipelines: Build ingestion and processing pipelines for structured, unstructured, and multimedia data. Optimize bulk data movement in S3, Glacier, and tiered storage.
- IoT Deployment: Manage infrastructure that deploys to and communicates with edge devices. Support secure messaging, identity, and over-the-air updates.
- Performance Optimization: Tune retrieval quality, context window use, and caching. Optimize inference with model selection, quantization, GPU/CPU instance choices, and autoscaling.
You will work closely with other engineers and product management. The ideal candidate is hands-on, comfortable with ambiguity, and excited to build from first principles.
REQUIREMENTS:
- Shipped or operated LLM-powered applications in production. Familiar with RAG design, prompt versioning, and chain orchestration using LangChain or similar.
- Strong with core AWS services: VPC, IAM, KMS, CloudWatch, S3, ECS/EKS, Lambda, Step Functions, Bedrock, and SageMaker.
- Comfortable building ingestion and transformation pipelines in Python. Familiar with Glue, Athena, and event-driven patterns using EventBridge and SQS.
- Security mindset: applies least privilege, secrets management, network isolation, and compliance practices.
- Uses quantitative evals, A/B testing, and live metrics to guide improvements.
- Clear communication: explains tradeoffs and aligns partners across product, security, and application engineering.
BONUS POINTS:
- 4+ years working with serverless or container platforms on AWS.
- Experience with vector databases, OpenSearch, or pgvector at scale.
- Hands-on 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 app services.
Hybrid role based in San Carlos, CA, with 3+ days per week onsite.
