Senior GenAI Architect for LLM & RAG Apps

Socket.dev; San Francisco (CA); On-site; USD 150,000 - 170,000; Full time

Benefits offered by this job

Unlimited PTO

Generous parental leave

Medical, Dental and Vision coverage

ESPP

Job summary

Socket.dev is seeking a hands‑on Generative AI and LLM Engineer to design, build and deploy production‑grade AI applications. You will own solutions end‑to‑end, from requirements to monitoring, with a focus on LLMs, RAG pipelines and intelligent agent workflows.

The role requires strong Python backend development experience and practical knowledge of vector databases, API integrations, Docker and cloud platforms.

Qualifications

• Bachelor's or Master's in Computer Science or related field.
• 6–9 years of professional software development with Python.
• Experience building backend services and REST APIs.
• Hands‑on experience with LLMs and Generative AI.
• Practical RAG using embeddings, vector databases and search.

Responsibilities

• Design and develop scalable LLM‑powered applications using Python.
• Build RAG pipelines with embeddings, vector databases and semantic search.
• Develop AI agent workflows with tool calling and memory.
• Integrate LLMs with internal systems and external APIs.
• Evaluate foundation models for accuracy, latency and cost.
• Improve prompt quality, retrieval accuracy and token efficiency.
• Implement safety guardrails, access controls and fallback mechanisms.
• Containerize apps with Docker and deploy on AWS, Azure or GCP.
• Set up monitoring and LLMOps for performance and costs.
• Collaborate with product and engineering to deliver reliable AI solutions.
• Document architecture, APIs and operational processes.

Skills

Python

LLM/Generative AI

Backend development

API integrations

Docker

Cloud platforms

Vector databases

LangChain/LangGraph

Team communication

Education

Bachelor's or Master's in CS

Tools

Docker

Kubernetes

LangGraph

Hugging Face

PyTorch

vLLM/Ollama

MLflow

Job description

Socket.dev is seeking a hands‑on Generative AI and LLM Engineer to design, build and deploy production‑grade AI applications. You will own solutions end‑to‑end, from requirements to monitoring, with a focus on LLMs, RAG pipelines and intelligent agent workflows.

The role requires strong Python backend development experience and practical knowledge of vector databases, API integrations, Docker and cloud platforms.