AI Agent Engineer (Skills & Prompts) at Pixalate | AdTechTalent
EngineeringRecentlyRemote
Pixalate
AI Agent Engineer (Skills & Prompts)
AI agentsLLMprompt engineeringagent skillsPythonTypeScriptevaluationad-techprogrammaticfraud detectionMCPSQLdata analysisremote
Key details
Salary
Not specified
Employment type
Full-time
Seniority
Mid-level
Years experience
3-5
Location
Lahore, Pakistan
Full job description
Pixalate is hiring a full-time AI Agent Engineer to build and maintain production AI agents that investigate invalid traffic and provide analytics. The role involves authoring and maintaining Claude skills, system prompts, and plugins that define agent behavior. Responsibilities include designing agents that ask clarifying questions, versioning prompts and skills, debugging agent failures, building evaluation suites, engineering context strategies, collaborating on tool design, tuning for cost and accuracy, and ensuring safety and trust in customer-facing agents. Candidates must have experience shipping LLM agents to real users, hands-on work with agent behavior tooling, evaluation discipline, strong written English, proficiency in Python or TypeScript, understanding of tool-calling, awareness of prompt injection and PII handling, and be comfortable with some U.S. timezone overlap. Ad-tech or fraud detection experience is preferred or candidates must be willing to learn quickly. Experience with MCP servers, observability, retrieval systems, and data analysis (including SQL) is a plus. The position is remote in Pakistan with a focus on Lahore location.
What you'll do
Author and maintain Claude skills and plugins defining agent capabilities and behavior
Similar jobs
More roles worth a look
Related opportunities based on specialty and working model so candidates can keep momentum.
Bellevue, United States; Boston, United States; Boulder, United States; Chicago, United States; Denver, United States; Los Angeles, United States; New York, US; San Francisco, United States; San Jose, United States; Seattle, United States; Ventura, United States•14 days ago
Design agents that ask clarifying questions and gather requirements interactively
Decide what belongs in a skill, system prompt, or tool
Maintain the skill library as products evolve
Own system prompts behind client-facing agents (IVT investigator agents, IQ Agent / Analytics MCP, MRT MCP)
Version prompts and skills with clear records of changes
Debug agent failures such as wrong tool selection, hallucinated findings, missed clarifying questions, context exhaustion
Define correctness criteria and build evaluation suites for agents
Build ground-truth datasets from real customer scenarios and measure changes
Catch regressions before customers do
Engineer context strategies for agent input within budget constraints
Collaborate with engineering on MCP tool surfaces and descriptions
Tune for cost, latency, and accuracy
Guard against prompt injection, data leakage, and unsafe tool use
Ensure agents represent findings accurately without overstating confidence
Requirements
Experience building LLM agents shipped to real users
Hands-on work with agent skills, plugins, system prompts, or equivalent agent-behaviour tooling
Experience with evaluation discipline including building eval suites and ground truth datasets
Strong written English skills
Working proficiency in Python or TypeScript
Comfort reading the codebase your agents run in
Understanding of tool-calling / function-calling and agent tool selection
Awareness of prompt injection, PII handling, and failure modes of customer-facing AI
Comfortable with some U.S. timezone overlap for team meetings
Ad-tech, digital advertising, or fraud-detection exposure preferred (programmatic, DSPs, SSPs, CTV, IVT, ad fraud concepts) or willingness to learn deeply in first 90 days
Experience with MCP servers or similar tool-integration standards is a plus
Experience with observability and tracing for LLM systems is a plus
Experience with retrieval systems and their failure modes is a plus
Data analysis background including SQL and working with large datasets is a plus
Competitive compensation packageMonthly internet reimbursementCasual, remote work environmentFlexible hoursOpportunity for advancement and professional developmentFun annual team eventsBeing part of a high-performing global team
Apply now
Ready to take the next step in your career? Click the button below to continue to the application process.
