Agentic Systems Engineer

Pakistan Digital Authority (PDA) is looking to hire an Agentic Systems Engineer based in Islamabad, Pakistan. This role involves designing, developing, and testing AI agents tailored for government applications. The position requires a combination of software engineering skills, retrieval techniques, and tool integration to build reliable AI-driven applications that perform user tasks under strict permission and oversight protocols. The successful candidate will work closely with cross-functional teams to ensure AI agents operate efficiently, securely, and transparently within defined governance frameworks.

Key Responsibilities
- Translate user requirements into effective agent workflows, choosing between single-agent or multi-agent architectures based on task complexity and reliability demands.
- Develop agent applications using frameworks such as LangGraph or model-provider SDKs.
- Integrate agents with authorized tools, APIs, and databases, leveraging the Model Context Protocol (MCP) where applicable.
- Build retrieval-augmented generation (RAG) pipelines utilizing vector and keyword search methods, ensuring access-aware retrieval and proper source referencing.
- Author, version, and test prompts, tool descriptions, and structured output formats.
- Enforce least-privilege access controls on tools, perform input/output validation, and implement human approval workflows for high-risk operations.
- Manage agent memory, context length, and sensitive data, ensuring proper retention policies and isolation between users.
- Design task evaluation sets and measure performance metrics such as task success rate, tool-call accuracy, execution steps, latency, and operational costs.
- Detect and resolve issues like incorrect tool calls, infinite loops, and unreliable outputs by applying execution limits, timeouts, and recovery mechanisms.
- Collaborate with MLOps engineers to trace agent execution, diagnose failures, and support controlled production deployments.

Required Qualifications
- Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related field.
- Minimum of 3 years’ experience in software engineering or AI application development, including at least 1 year focused on building large language model (LLM)-based applications.
- Proven hands-on experience delivering applications involving tool calling, retrieval-augmented generation, or agent workflow design.
- Strong proficiency in Python or TypeScript, API integration, database management, Git version control, and software testing methodologies.
- Practical knowledge of prompt engineering, retrieval systems, agent state and memory management, structured output generation, and application performance evaluation.
- Capability to implement permission controls and human-in-the-loop approval processes, combined with excellent debugging, documentation, and teamwork skills.

Preferred Qualifications and Experience
- Familiarity with LangGraph or similar agent development frameworks, Model Context Protocol (MCP) integrations, and hybrid search technologies.
- Experience mitigating risks such as prompt injection, unsafe tool execution, and unauthorized data access in AI systems.
- Exposure to government workflows, multilingual AI applications, or enterprise environments requiring audit trails and human oversight.

Applications will be accepted for 15 days from the publication date, but submissions may continue to be reviewed until the position is filled. Interested candidates should refer to the official Pakistan Digital Authority careers page for further details and apply accordingly.

Job Details

Total Positions:

1 Post

Job Shift:

Full Time

Job Type:

First Shift (Day)

Job Location:

Islamabad, Pakistan

Gender:

No Preference

Age:

18 - 65 Years

Minimum Education:

Master

Degree Title:

Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related discipline. At least 3 years of relevant experience in software engineering or AI application development, including at least 1 year buil

Career Level:

Mid-Level

Maximum Experience:

2 Years

Apply Before:

Nov 04, 2026

Posting Date:

Oct 29, 2026