AI Jobs Map

Alchemy · Santa Clara, CA 95056

LLM Application Architect

Hybridfull timePosted 23 days ago
Apply on IndeedIndeedOpens the original posting. AI Jobs Map never asks for your details.

Stack mentioned

llmragpythonlangchainllamaindexai-safetyprompt-engineeringvector-databasesartificial-intelligence

We are seeking a Senior AI/LLM Application Engineer with strong production experience building and optimizing LLM-powered applications, RAG pipelines, AI safety, and multi-step LLM workflows. This is a hands-on engineering role focused on production AI quality, accuracy, latency, evaluation, and safety.

Must-Have Skills

- 10+ years total IT experience

- 4–7 years software engineering experience with 2+ years building LLM applications in production

- Strong Python development experience

- Expert LLM prompt engineering

- Expert experience with LangChain, LlamaIndex, or custom LLM orchestration

- Strong RAG pipeline design and optimization

- Experience with embeddings, vector search, chunking, retrieval, and reranking

- Hands-on RAG evaluation using RAGAS, TruLens, or equivalent

- Experience with AI safety, guardrails, prompt injection, and jailbreak testing

- Experience optimizing multi-step LLM chains for latency, cost, and accuracy

- Experience with LLM evaluation, benchmarking, regression testing, and production monitoring

- Strong experience with multi-turn conversations, streaming responses, and session memory

- Experience building AI APIs and production-ready AI services

Responsibilities

- Build and optimize production-grade LLM and RAG applications.

- Design multi-step LLM orchestration and conversational workflows.

- Develop automated RAG/LLM evaluation frameworks and quality gates.

- Implement AI safety, guardrails, hallucination mitigation, and prompt-injection protection.

- Optimize model selection, latency, cost, retrieval accuracy, and response quality.

- Develop feedback loops to improve retrieval and model performance.

- Monitor production AI quality and identify performance or accuracy degradation.

- Work closely with product, engineering, and security teams to deliver reliable AI solutions.

Application Question(s):

- Do you have expert-level Python experience for AI/ML application development?

Experience:

- LLM applications in production: 3 years (Required)

Work Location: Hybrid remote in Santa Clara, CA 95056

More jobs at Alchemy