Senior Software Engineer – Artificial Intelligence/LLM

Beacon Venture Capital

. Design and implement retrieval-augmented generation and tool-calling flows .

Posted 10/3/2026full-timeSan Carlos • California • United StatesSenior💰 $173,000 - $225,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

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

Demonstrates expertise in designing and implementing retrieval-augmented generation systems, with a strong focus on integrating LLM features and optimizing performance metrics. Proficient in production coding, testing, and documentation, while ensuring compliance with safety-critical domain standards.

Highest-signal resume keywords

Production ML/LLM Systems ExperienceLLM Feature Shipping and ImprovementEmbeddings and Vector Search UnderstandingA/B Testing and Metrics EvaluationDevOps Basics for CI/CD and IaC

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

PythonTypeScriptJSONEmbeddingsChunkingFunction CallingPrompt VersioningLatency TrackingData SynchronizationContent and Policy Checks

Soft Skills

CollaborationProblem-SolvingOwnershipAttention to DetailAdaptability

Tools & Technologies

AWS BedrockOpenSearchPgvectorPineconeDynamoDBS3TritonTensorRT-LLMCI/CDIaC

Industry Keywords

AviationSafety-Critical DomainMultimodal WorkGPU InferenceData Services

Tech Stack

Tools & technologies

AWSDynamoDBPythonTypeScript

About the role

Key responsibilities & impact

Design and implement retrieval-augmented generation and tool-calling flows
Deliver robust JSON and schema-bound outputs with validation, retries, and fallbacks
Integrate function calling with internal tools, search, routing, and data services
Ship APIs and workers in Python or TypeScript with clear contracts, streaming, and backoff
Add caching, request shaping, prompt templates, and context packing to control latency and cost
Integrate with AWS Bedrock, OpenAI, Anthropic, or self-hosted endpoints
Collaborate on chunking, embeddings, and indexing for documents, time series, and multimedia
Choose and tune vector backends such as OpenSearch, pgvector, or Pinecone
Maintain knowledge bases through data synchronization from S3, Aurora, DynamoDB, and external sources
Create offline evaluations and golden sets for prompts, retrievers, and tools
Establish online metrics for task success, hallucination rate, retrieval precision/recall, p95 latency, and cost per request
Run A/B tests and prompt/version rollouts with guardrails and canaries
Implement content and policy checks, PII detection and redaction, access controls, and auditing
Design human-in-the-loop paths for sensitive actions
Add tracing, logs, and dashboards for model calls, token usage, errors, and saturation
Debug failures across retrieval, prompts, tools, and providers
Partner with product, infrastructure, ML, and security teammates to deliver reliable aviation systems
Build user-facing LLM features for Beacon AI’s platform that makes flying safer, more efficient, and more capable

Requirements

What you’ll need

5–8 years of experience, including some experience in production ML/LLM systems
Experience shipping LLM features to users and improving them with data
Production coding, testing, and documentation skills
Understanding of embeddings, chunking, vector search tradeoffs, and function calling
Experience designing evaluations, defining success metrics, and iterating based on evidence
Ability to track p95 latency, meet SLAs, and reduce cost without compromising quality
Ability to own features from design through production with minimal oversight
Experience with Bedrock, OpenSearch Serverless, pgvector, Pinecone, or Weaviate preferred
Experience with prompt versioning, guardrails, and provider routing preferred
Multimodal work with time series or video preferred
Familiarity with GPU inference, Triton, or TensorRT-LLM preferred
Aviation or other safety-critical domain exposure preferred
DevOps basics for CI/CD, IaC, and secure secrets handling preferred
Must be a U.S. Person
Must be authorized to work lawfully in the United States
No visa sponsorship or visa transfers available
All work must be performed in the United States
Must be based in or willing to relocate to the San Francisco Bay Area
Must work onsite in San Carlos, CA, 3+ days per week
Full-time availability

Benefits

Comp & perks

Offers equity
100% of employee medical premiums covered
25% of dependent medical premiums covered
3 weeks PTO
13+ paid company holidays
401(k) offered
Flexible remote work on remaining days of the hybrid schedule