Latest AI JobsBrowse Jobs
B

Staff Software Engineer, Artificial Intelligence/LLM

beaconaiSan Carlos - HybridEngineering
Apply on company site
Salary
$224K – $260K
Job type
Full-time
Experience
Senior · 8+ yrs
Posted
2 Oct 2026
Status
Open · checked 7d ago

About this role

This hybrid role is based in San Carlos, California, requiring three or more days onsite per week with remote options for remaining days. It suits an experienced engineer with technical leadership capabilities who wants to build safety-critical aviation platforms powered by artificial intelligence.

Role Overview

Beacon AI is hiring a Staff Software Engineer for Artificial Intelligence and Large Language Models to shape technical direction across services and teams at an L6 level. The professional joining this position will design and deliver end-to-end LLM-powered product features, manage retrieval frameworks, and handle production metrics including latency and cost in a safety-critical domain.

Key Responsibilities

Build user-facing retrieval-augmented generation and tool-calling flows utilizing frameworks such as LangChain, while implementing validation, retries, fallbacks, and schema-bound outputs.
Own the service layer by writing APIs and workers in Python or TypeScript, integrating caching, streaming, context packing, and connections to AWS Bedrock, OpenAI, Anthropic, or self-hosted endpoints.
Collaborate with infrastructure peers on chunking, embeddings, indexing, vector backends like OpenSearch, pgvector, or Pinecone, and data syncs from S3, Aurora, and DynamoDB.
Create offline evaluations, golden sets, online metrics for hallucinations and task success, and run A/B tests with proper guardrails.
Implement PII detection, content checks, access controls, auditing, and human-in-the-loop pathways for sensitive actions.
Operate production systems by adding tracing, logs, dashboards, and debugging complex failures across retrieval, prompts, and tool integrations.

Requirements

Possess 8+ years of professional software engineering experience with a demonstrated track record of owning systems or establishing standards for other engineers.
Hands-on experience shipping LLM applications to users and improving them based on data.
Strong coding background in writing production code, tests, and documentation with a focus on simplicity and observability.
Deep understanding of RAG architectures, embeddings, vector search tradeoffs, and function calling.
Experience designing evaluations, tracking p95 latency, meeting SLAs, and reducing operational costs.
Ability to communicate clearly and align cross-functional partners across product, infrastructure, and security.

Nice to Have

Practical background using AWS Bedrock, OpenSearch Serverless, pgvector, Pinecone, or Weaviate.
Production use of prompt versioning, guardrails, and provider routing.
Multimodal project work involving time series data or video.
Familiarity with GPU inference, Triton, or TensorRT-LLM.
Prior exposure to aviation or other safety-critical industries.
DevOps fundamentals covering CI/CD, Infrastructure as Code, and secure secrets handling.

Skills and Tools

Python
TypeScript
LangChain
AWS Bedrock
OpenAI
Anthropic
OpenSearch
pgvector
Pinecone
Weaviate
S3
Aurora
DynamoDB
Triton
TensorRT-LLM

Salary and Benefits

The base salary range is $224,000 to $260,000 per year, complemented by equity offers. Comprehensive employee benefits include 100% coverage of employee medical premiums and 25% for dependents, 3 weeks of paid time off, 13+ paid company holidays, and a 401(k) plan.

About the Company

Beacon AI builds an AI platform designed to make aviation safer, more efficient, and more capable. Backed by top investors, the organization holds Department of Defense contracts and airline partnerships to deliver mission-critical systems through small, focused teams operating without heavy silos.

How to Apply

Interested candidates should apply on the official company careers page.

Skills and tech stack

PythonTypeScriptLangChainAWS BedrockOpenAIAnthropicOpenSearchpgvectorPineconeWeaviateS3AuroraDynamoDBTritonTensorRT-LLMLLMRAGAWS

Questions candidates ask

What is the location and work setup for this role?

The position is hybrid, based in San Carlos, California. It requires working onsite at least three days per week, with the option to work remotely on the remaining days.

What experience level is required for this position?

The role requires 8+ years of experience and is set at the L6 staff level, calling for candidates with a track record of owning systems or defining technical standards for others.

What compensation and benefits are provided?

The base salary ranges from $224K to $260K with equity. Benefits include 100% coverage for employee medical premiums, 25% for dependents, 3 weeks of PTO, 13+ paid holidays, and a 401(k) plan.

Is visa sponsorship available?

No. Due to U.S. export control regulations, the company can only hire U.S. Persons and is unable to provide visa sponsorship or support visa transfers.

What programming languages and tools are used in this role?

The tech stack includes Python, TypeScript, LangChain, AWS Bedrock, OpenAI, Anthropic, OpenSearch, pgvector, Pinecone, and vector database technologies.

Ready to apply?

The application is on the official beaconai careers page.

Apply on company site