Software Engineer, Artificial Intelligence/LLM

What you'll do

• Build user-facing LLM features: Design and implement retrieval-augmented generation and tool-calling flows using frameworks like LangChain (prefer simpler primitives). Deliver robust JSON/schema-bound outputs with validation, retries, and fallbacks. Add function calling to integrate with internal tools, search, routing, and data services.
• Own the service layer: 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.
• Retrieval and data prep: Collaborate on chunking, embeddings, and indexing for documents, time series, and multimedia. Choose and tune vector backends (OpenSearch, pgvector, Pinecone). Keep knowledge bases fresh via syncs from S3, Aurora, DynamoDB, and external sources.
• Evaluation and quality: Create offline evals and golden sets for prompts, retrievers, and tools. Stand up 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.
• Safety, privacy, and compliance: Implement content/policy checks, PII detection/redaction, access controls, and auditing. Design human-in-the-loop paths. Handle aviation data per internal security standards.
• Operate what you build: Add tracing, logs, and dashboards for model calls, token usage, errors, and saturation. Debug failures across retrieval, prompts, tools, and providers.

Requirements

• Shipped LLM apps in production and improved them with data.
• Strong builder: comfortable writing production code, tests, and docs; keep things simple and observable.
• Deep RAG and tools experience: understand embeddings, chunking, vector search tradeoffs, and function calling.
• Quality mindset: design evals, define success metrics, iterate on evidence.
• Cost and latency aware: track p95, hit SLAs, reduce cost without sacrificing quality.
• Clear communicator: explain tradeoffs and align with product, infra, and security partners.

Nice-to-haves

• Experience with Bedrock, OpenSearch Serverless, pgvector, Pinecone, or Weaviate.
• Prompt versioning, guardrails, and provider routing in production.
• Multimodal work with time series or video.
• Familiarity with GPU inference, Triton, or TensorRT-LLM.
• Aviation or safety-critical domain exposure.
• DevOps basics (CI/CD, IaC, secure secrets handling).

Compensation & Benefits

• Salary: $135,000 - $260,000 (varies by level)
• Healthcare: 100% employee medical premiums covered; 25% for dependents
• Time off: 3 weeks PTO + 13+ paid company holidays
• Monthly phone and wellness stipends
• 401(k) offered