AI Engineer, Agent Workflows

Govini•Pittsburgh, PA

2h•Onsite

About The Position

We are seeking an experienced AI Engineer to join our Agentic AI team as we scale our agentic offerings across all levels of the US government. Over the past year, we have seen the rapid adoption of our agent, Ace. We expect Ace to be handling much more complex tasks and workflows end-to-end or in cooperation with a human user as time goes on. The team is striving to make Ace an even more effective agent, focusing on planning, reliable execution over longer time horizon tasks, scaled tool use, Ace Skills, memory, and inter-agent coordination. In order to do this job well, we are looking for someone who can demonstrate a project built on LLMs that showcases your skill at getting them to do complex tasks. Experience integrating and working with LLMs, with a strong understanding of their capabilities and limitations Experience integrating and working with agent frameworks like Claude Agent SDK or OpenAI Agent SDK Experience building observability, evaluation, and feedback loops for agent behavior (telemetry, prompt evaluation, regression testing, and reliability metrics). Experience working in highly ambiguous environments, and operate with urgency Startup experience, particularly in scaling products from zero to one This role is a full-time position located out of our office in Pittsburgh, PA. This role may require up to 10% travel

Requirements

U.S. Citizenship is required
Bachelor's, Master’s, or Doctorate in Computer Science, Computer Engineering, Data Science, or a related field
Minimum 3 years of experience building and deploying ML or LLM-powered systems in production environments
Practical experience in building, developing, and productionizing machine learning systems
Advanced software skills in Python
Experience with common LLM algorithms and implementations
Hands-on experience with AWS and cloud infrastructure
A strong desire to learn and investigate new technologies
Familiarity with Git source control management
Ability to work collaboratively with little supervision
A burning desire to work in a challenging, fast-paced tech environment

Nice To Haves

Current possession of a U.S. security clearance, or the ability to obtain one with our sponsorship
Experience in or exposure to the nuances of a startup or other entrepreneurial environment
Experience with modern front-end frameworks (e.g., React, Next.js, or similar) and API-driven UI architectures
Comfortable with Claude Code and GenAI coding best practices.

Responsibilities

Inform and implement the design and development of NLP applications to enhance the intelligence and efficiency of our data analytics software-as-a-service platform
Review, verify, and aggregate the most appropriate annotated datasets for the best supervised learning methods
Ability to work with taxonomy experts to create and validate dataset annotation
Use well-formed and effective text representation to change and adapt natural language documents into user-friendly features
Implement the latest technology to improve user search functionality, and integrate state-of-the-art LLM models into our Ark.ai platform to enhance the user experience.
Develop new algorithms and modeling techniques, and conduct sound experiments to verify model results and integrate models into the live production system
Establish meaningful criteria for evaluating algorithm performance and suitability.
Implement working, scalable, production-ready models and code
Keep up to date with Machine Learning best practices and evolving open-source frameworks
Regularly seek out innovation and continuous improvement, finding efficiency in all assigned tasks
Collaborate closely with fellow taxonomists, software engineers, data scientists, data engineers, and QA engineers