AI Platform Engineer/ Hybrid/ LangChain/LangGraph

We are looking for a Senior Python / GenAI Engineer with strong experience building cloud-native applications and developing solutions powered by large language models. In this role, you will help design and implement scalable AI-driven services within a modern cloud environment, working closely with engineering teams to build APIs, optimize inference pipelines, and deliver production-ready GenAI applications.

Full Desk, Direct Hire role.

Hybrid opportunity in the Houston area.

Primarily a backend engineering role focused on AI platform development.

What you will be doing

Tech Breakdown

70% new development

30% optimization, support, and enhancements

Daily Responsibilities

Design and implement scalable APIs and shared software services using Python

Build and support applications on an AI platform leveraging modern GenAI technologies

Develop LLM-powered applications using tools like LangChain or LlamaIndex

Work with Azure OpenAI and/or Google GenAI APIs to integrate LLM capabilities into production systems

Build cloud-native applications in Azure and GCP

Implement serverless architectures and containerized workloads using Docker and Kubernetes

Design, monitor, and optimize AI inference and data pipelines to improve performance and efficiency

Troubleshoot issues across application code, cloud environments, and AI services

Document architecture, APIs, and internal AI platform components

Collaborate with internal engineering and support teams to deliver scalable AI-driven solutions

Contribute to architecture discussions and continuously improve system performance, security, and scalability

Develop proof-of-concepts (POCs) to evaluate emerging AI technologies and their potential business impact Experience / Requirements

7+ years of full software development lifecycle experience including design, development, testing, deployment, and support

Strong Python development experience

Deep understanding of object-oriented design principles, design patterns, and scalable architecture

Proven experience designing and implementing APIs and backend services

Hands-on experience building and deploying applications in Azure and/or Google Cloud Platform

Strong understanding of cloud scaling concepts and distributed systems

2+ years of experience building LLM-based applications

Experience implementing RAG architectures, embeddings, vector databases, agents, and fine-tuning

Experience with LLM orchestration frameworks such as LangChain or LlamaIndex

Hands-on experience integrating OpenAI / Azure OpenAI / Google GenAI APIs

Experience with containerization and orchestration (Docker, Kubernetes)

Familiarity with version control tools such as Git / Azure DevOps

Experience writing Azure DevOps YAML pipelines for CI/CD

Experience with at least one additional object-oriented language such as Java, C#, or C++

Strong communication skills and ability to work both independently and within collaborative engineering teams Nice to Have

AWS cloud experience

Experience with Databricks or Apache Spark

Knowledge of data warehousing and data lake architectures

Experience working with relational databases and SQL

Terraform infrastructure-as-code experience

Experience building AI platform components or internal developer platforms Education

Bachelor's degree in Computer Science, Information Systems, or a related technical field

Specialization :

Data and AI Security

Python