Software Engineer, Artificial Intelligence/LLM (Multiple Seniority Levels)

Responsibilities

Build user-facing LLM features

• Design and implement retrieval-augmented generation and tool-calling flows using frameworks like LangChain or equivalent primitives.
• Deliver robust JSON and 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 such as OpenSearch, pgvector, or Pinecone.
• Keep knowledge bases fresh with data syncs from S3, Aurora, DynamoDB.

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.
• Run A/B tests and prompt/version rollouts with guardrails and canaries.

Safety, privacy, and compliance

• Implement content and policy checks, PII detection and redaction, access controls, and auditing.
• Design human-in-the-loop paths for sensitive actions.

Operate what you build

• Add tracing, logs, and dashboards for model calls, token usage, errors, and saturation.

Requirements

• Shipped LLM apps and improved them with data.
• Strong builder: production code, tests, and docs; keep things simple and observable.
• RAG and tools depth: embeddings, chunking, vector search tradeoffs, function calling.
• Quality mindset: evals, success metrics, iterate on evidence.
• Cost and latency aware: track p95, hit SLAs, reduce cost.
• Clear communicator: explain tradeoffs, align partners.

Nice to Have

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