Lead Python AI Engineer

Salt; Atlanta (GA); On-site; USD 180,000 - 240,000; Full time

Job summary

Salt is seeking a Lead Python AI Engineer to design scalable, AI-powered backend services, APIs, and agentic workflows. You will bridge backend engineering with AI tech, integrating LLMs, vector databases, and external tools into production-grade systems.

The ideal candidate has 7+ years in backend, strong Python and distributed systems, and hands-on AI SDK experience. You will own API contracts, ensure security, and collaborate across teams to deliver robust AI solutions.

Qualifications

• 7+ years of backend engineering experience, with strong Python, microservices and distributed systems expertise.
• Experience designing and developing scalable, cloud-native APIs and backend services.
• Hands-on experience with AWS, Docker, ECS/EKS, and RESTful APIs.
• 1-2+ years of production experience integrating AI SDKs (OpenAI, Anthropic/Claude, AWS Bedrock).
• Practical experience with agentic AI frameworks (LangChain, LangGraph, LlamaIndex).
• Experience building and optimizing RAG pipelines, vector databases, embeddings, and retrieval systems.
• Familiarity with vector search tech like Amazon Kendra or OpenSearch.
• Understanding AI observability and evaluation tools (LangSmith, Langfuse, Arize).
• Strong knowledge of secure coding practices, authentication, authorization and API security.
• Ability to design reliable, maintainable, production-grade AI applications.
• Nice to have React and TypeScript experience.
• Experience deploying and scaling apps within AWS EKS environments.
• Familiarity with MCP and agent interoperability.
• Understanding IAM and CIAM.

Responsibilities

• Design, develop, and maintain scalable backend API services and LLM orchestration layers.
• Own API contracts, service reliability, performance, and graceful failure handling.
• Build and optimize RAG pipelines with document ingestion, embeddings, and retrieval strategies.
• Develop reusable agentic workflows using LangChain, LangGraph, and LlamaIndex.
• Integrate LLMs with internal systems, vector databases, and external tools.
• Implement AI evaluation, observability, fallback mechanisms, and cost optimization.
• Contribute to architecture, standards, and best practices across teams.
• Collaborate with frontend, data engineering and infrastructure teams to deliver scalable AI solutions.

Skills

Python

Backend engineering

Microservices

Distributed systems

LLM orchestration

RAG pipelines

LangChain

LangGraph

LlamaIndex

Vector databases

Embeddings

Retrieval systems

AWS

Docker

RESTful APIs

AI observability tools

LangSmith

Langfuse

Arize

Security / API security

IAM / CIAM

React

TypeScript

Java

Node.js

Go

MCP

Tools

Docker

Kubernetes / EKS

OpenAI

Anthropic/Claude

AWS Bedrock

Job description

About the Company

Our client is a global technology and digital engineering organization that partners with leading businesses to design, develop, and deliver innovative technology solutions. With a strong focus on cloud engineering, artificial intelligence, and digital transformation, the company helps organizations solve complex technical challenges and build scalable, future-ready platforms.

About the Role

We are seeking an experienced Lead Python AI Engineer to design and build scalable, AI-powered backend services, APIs, and intelligent agentic workflows. In this role, you will bridge traditional backend engineering with modern AI technologies, integrating Large Language Models (LLMs), vector databases, and external tools into secure, reliable, production-grade systems. The ideal candidate combines strong Python and distributed systems expertise with hands-on experience in LLM orchestration, Retrieval-Augmented Generation (RAG), and agentic AI frameworks.

Key Responsibilities

• Design, develop, and maintain scalable backend API services and advanced LLM orchestration layers.
• Take end-to-end ownership of API contracts, service reliability, performance, and graceful failure handling.
• Build and optimize RAG pipelines, including document ingestion, chunking, embeddings, and retrieval strategies.
• Develop reusable agentic workflows and orchestration frameworks using tools such as LangChain, LangGraph, and LlamaIndex.
• Integrate LLMs with internal systems, vector databases, and external tools.
• Implement AI evaluation, monitoring, observability, fallback mechanisms, and cost optimization strategies.
• Ensure enterprise-grade security, data privacy, authentication, and comprehensive testing across backend services.
• Contribute to technical architecture, engineering standards, and best practices.
• Collaborate with frontend, data engineering, and infrastructure teams to deliver scalable AI solutions.

Required Skills & Experience

• 7+ years of backend engineering experience, with strong expertise in Python, microservices, and distributed systems.
• Proven experience designing and developing scalable, cloud-native APIs and backend services.
• Hands-on experience with AWS, Docker, ECS/EKS, and RESTful APIs.
• 1-2+ years of production experience integrating AI SDKs such as OpenAI, Anthropic/Claude, AWS Bedrock, or similar technologies.
• Practical experience with agentic AI frameworks, including LangChain, LangGraph, or LlamaIndex.
• Experience developing and optimizing RAG pipelines, vector databases, embeddings, and retrieval systems.
• Familiarity with vector search technologies such as Amazon Kendra or OpenSearch.
• Understanding of AI observability and evaluation tools such as LangSmith, Langfuse, or Arize.
• Strong knowledge of secure coding practices, authentication, authorization, and API security.
• Ability to design reliable, maintainable, and production-ready AI applications.
• Nice to Have Experience with React and TypeScript.
• Experience deploying and scaling applications within AWS EKS environments.
• Familiarity with Model Context Protocol (MCP) and agent interoperability.
• Understanding of Identity and Access Management (IAM) and Customer Identity and Access Management (CIAM).
• Additional programming experience with Java, Node.js, or Go.

Why Consider This Opportunity?

This is an opportunity to work on advanced AI engineering initiatives, building intelligent systems that go beyond experimentation and into real-world production environments. You will have the opportunity to influence technical architecture, develop reusable AI frameworks, and collaborate with experienced engineering teams on complex, large-scale technology solutions. If you are a hands-on Python engineer with a passion for building reliable, scalable AI systems, we'd love to hear from you.

Salt is acting as an Employment Agency in relation to this vacancy.