Production AI/ML Systems Engineer (Python, GPU/Kubernetes)

Cogniify, Inc.; Santa Clara, Northern (CA, KY); Hybrid; USD 150,000 - 230,000; Full time

Benefits offered by this job

Unlimited PTO

Generous parental leave

Open communication with management

Small, dynamic teams = massive impact

Medical, Dental and Vision coverage

Disability & Life insurance

ESPP

Yearly team building experiences

Mentorship and sponsorship

Job summary

Cogniify, Inc. is seeking a Software Engineer, AI/ML Systems to build, evaluate and deploy AI-powered applications and services.

This hands-on role combines production Python development, AI model evaluation, distributed deployment and automated testing. We are looking for someone who can take ownership of AI features from design through production, work with open-source models and AI agents, and improve system quality through reliable CI/CD pipelines and security automation.

Qualifications

• 4+ years of professional experience developing production-grade Python applications.
• Experience deploying, monitoring and scaling AI/ML models in production using Kubernetes, Ray, Slurm or similar orchestration tools.
• Experience with LLM development and evaluation tools such as Hugging Face, LangChain, vLLM or SG Lang, including prompt engineering and systematic benchmarking.
• Strong understanding of GPU-backed model serving, memory considerations and performance optimisation for high-throughput, low-latency inference.
• Experience analysing model and application results using Python libraries such as pandas and NumPy.
• Strong GitLab CI/CD experience, including automated testing, merge request workflows and integration of vulnerability scanning.
• Experience with PyTest, mocking tools and automated tests for APIs, services and AI applications.
• Good working knowledge of Git, including branching, rebasing, code review and secure collaboration practices.
• Ability to work independently, explain technical findings clearly and take responsibility for production quality.

Responsibilities

• Build and maintain production AI/ML applications and Python services, with clean architecture and asynchronous programming.
• Deploy and scale AI models and workloads using Kubernetes, Ray or Slurm across distributed infrastructure.
• Design and evaluate AI agents and LLM workflows, including prompt tuning, model comparisons and performance benchmarking.
• Analyze model outputs, identify errors and quality gaps, and build clear reports or dashboards for stakeholders.
• Develop automated unit, integration and end-to-end tests for software components and AI workflows.
• Build and improve GitLab CI/CD pipelines for automated testing, code quality checks, and vulnerability scanning.
• Work on GPU memory usage, inference throughput and latency to improve model serving efficiency.
• Maintain sound Git practices and collaborate across code repositories, including public/private projects when required.
• Own assigned features from requirements and design through deployment, monitoring and troubleshooting.

Skills

Async programming

Software architecture

Design patterns

Model evaluation

Performance benchmarking

Independent work

Tools

Kubernetes

Ray

Slurm

Hugging Face

LangChain

vLLM

SGLang

GitLab CI/CD

PyTest

NumPy

pandas

Git

Job description

Cogniify, Inc. is seeking a Software Engineer, AI/ML Systems to build, evaluate and deploy AI-powered applications and services.

This hands-on role combines production Python development, AI model evaluation, distributed deployment and automated testing. We are looking for someone who can take ownership of AI features from design through production, work with open-source models and AI agents, and improve system quality through reliable CI/CD pipelines and security automation.