Generative AI Engineer – AI Platform & Agentic AI

DynPro Inc.; San Francisco (CA); Sur place; USD 150 000 - 210 000; Plein temps

Résumé du poste

DynPro Inc. seeks a hands-on Generative AI Engineer to design, develop, deploy, and support enterprise-scale AI applications and platforms in San Francisco. You will work with Python, LiteLLM, LangChain/LangGraph, and AWS to build scalable AI solutions.

The role focuses on instrumenting AI gateways, agentic workflows, and observability, ensuring secure, cost-efficient production systems while collaborating with product and data science teams.

Qualifications

• 5+ years in Software/AI platform roles or equivalent.
• Hands-on Python programming and backend development.
• Production experience with LLMs, prompt engineering, and tool integration.
• Experience with LiteLLM, LangChain/LangGraph, and orchestration frameworks.
• Hands-on with AI agents and agentic workflows.
• Knowledge of LLM evaluation, monitoring, and observability.

Responsabilités

• Design, develop, deploy, and support enterprise Generative AI applications and platforms.
• Build and manage LLM gateways (LiteLLM) including routing, caching, fallbacks, and guardrails.
• Develop AI agents and agentic workflows with LangGraph, CrewAI, or equivalents.
• Integrate MCP servers with enterprise tools, APIs, databases, Slack, and Jira.
• Implement LLM observability, including latency, token usage, and cost optimization.
• Develop LLM evaluation frameworks with datasets and quality metrics.
• Support RAG pipelines, vector databases, embeddings, and retrieval optimization.
• Collaborate with engineering, data science, and product teams for production-ready solutions.
• Manage AWS cloud infrastructure, Terraform, and CI/CD pipelines.

Connaissances

Python programming

LLM/AI engineering

Platform engineering

DevOps

REST API integration

Formation

Bachelor's degree in CS or related field

Outils

LiteLLM

LangChain

LangGraph

Terraform

AWS

GitHub Actions

Description du poste

We are seeking a hands-on Generative AI Engineer to design, develop, deploy, and support enterprise-scale AI applications and platforms. The ideal candidate will have strong experience with LLMs, AI Agents, Python, LiteLLM, LangChain/LangGraph, AWS, and AI/ML infrastructure.

This role focuses on building scalable AI platforms, developing agentic workflows, integrating enterprise AI tools, and ensuring the reliability, security, observability, and cost efficiency of production AI systems.

Key Responsibilities

• Design, develop, and maintain enterprise Generative AI applications, LLM infrastructure, and AI platforms.
• Build and manage LLM gateways (LiteLLM), including model routing, caching, fallbacks, cost tracking, and guardrails.
• Develop AI agents and agentic workflows using LangGraph, CrewAI, or similar frameworks.
• Integrate MCP (Model Context Protocol) servers with enterprise tools, APIs, databases, Slack, and Jira.
• Implement LLM observability and monitoring, including response quality, token usage, latency, hallucination detection, and cost optimization.
• Build LLM evaluation frameworks, including golden datasets, LLM-as-judge, regression testing, and quality metrics.
• Develop and support RAG pipelines, vector databases, embeddings, and retrieval optimization.
• Support enterprise AI platforms such as Glean, Gemini Enterprise, or Claude Cowork.
• Manage AWS cloud infrastructure, Terraform, and CI/CD pipelines.
• Collaborate with engineering, data science, and product teams to deliver production-ready AI solutions.

Required Skills & Qualifications

• 5+ years of experience in Software Engineering, AI/ML Engineering, Platform Engineering, or DevOps.
• Strong hands-on Python programming, backend development, and REST API integration.
• Production experience with LLMs, LLM APIs, prompt engineering, function calling, and tool integration.
• Experience with LiteLLM, LangChain, LangGraph, or similar LLM orchestration frameworks.
• Hands-on experience developing and deploying AI agents and agentic workflows.
• Experience with LLM evaluation, testing, and monitoring.
• Familiarity with enterprise AI platforms such as Glean, Gemini Enterprise, or similar solutions.
• Strong experience with AWS, Terraform, and CI/CD tools such as GitHub Actions, Jenkins, or Azure DevOps.
• Understanding of scalable AI infrastructure, troubleshooting, and production deployment.

Preferred Qualifications

• Experience building or integrating MCP servers.
• Experience with LLM observability tools such as LangSmith, Arize, Braintrust, or Datadog.
• Hands-on knowledge of RAG, vector databases, embeddings, and semantic search.
• Experience implementing LLM guardrails, security, and prompt injection protection.
• Knowledge of Amazon Bedrock, AWS Lambda, and serverless AI architectures.
• Experience with LLM cost optimization, semantic caching, and intelligent model routing.
• Background working in enterprise SaaS or large-scale software environments.

Ideal Candidate

A hands-on GenAI / AI Platform Engineer who has built and supported production LLM applications, AI agents, and AI infrastructure, with strong Python, cloud engineering, and AI platform integration experience.