Software Engineer

We are looking for a Software Engineer with strong experience in AI/LLM systems and code intelligence to build next-generation systems that help identify and reason about privacy risks in large-scale codebases.

The focus of this role is to design and build systems that can analyse source code to understand:

• Where sensitive or personal data may be collected
• How data flows through the system
• Where external integrations or third-party services exist
• Whether sensitive data may be shared, transmitted, or exposed externally

You will work at the intersection of AI, code understanding, and large-scale analysis systems, building intelligent pipelines that combine static analysis techniques with LLM-based reasoning to surface meaningful privacy insights.

Responsibilities:

• Build AI/LLM-powered systems to analyse source code for privacy-related risks and data handling patterns.

Design pipelines to identify:

• Potential collection of sensitive or personal data in code.
• Data flow paths from collection points to storage, processing, or external systems.
• Integration points with third-party services and external APIs.
• Potential exposure or sharing of sensitive data.

Develop LLM-based workflows for:

• Code understanding and semantic interpretation.
• Classification of data handling logic.
• Enrichment of static analysis outputs with contextual insights.
• Summarisation of privacy risk findings.
• Build systems that process large codebases and generate structured privacy intelligence reports.
• Design and implement RAG pipelines, prompt strategies, and agent-based workflows for code analysis use cases.
• Improve accuracy, scalability, and reliability of AI-driven code analysis systems.
• Collaborate with engineering teams to integrate privacy insights into developer and governance workflows.

Requirements:

• Strong software engineering and system design skills.
• Hands-on experience building LLM/Generative AI-based applications.
• Experience working on AI systems for code understanding, analysis, or developer tooling.
• Strong programming experience in at least one language (Python, Java, Go, etc. ).
• Experience with LLM APIs (OpenAI, Anthropic, or open-source models).
• Understanding of: Prompt engineering, RAG (Retrieval Augmented Generation), Embeddings and vector databases, Agent-based architectures.
• Experience building production-grade systems with a focus on scalability and reliability.

Good to Have:

• Experience with code analysis, static analysis, or program analysis systems.
• Familiarity with these concepts will be a plus: AST (Abstract Syntax Trees), Data flow analysis.
• Program structure and code representation.
• Experience working with large-scale codebases or monorepos.
• Exposure to privacy, data governance, or compliance-related systems (GDPR, CCPA, etc. ).
• Experience building or working with coding agents or AI developer tools.

Nice to Have:

We are looking for engineers who are excited about building AI systems that understand how data flows through code and help surface privacy risks in complex software systems.

You should be comfortable:

• Designing LLM-powered systems that reason about code behaviour.
• Working with structured and unstructured code data.
• Building intelligent pipelines that combine AI and programmatic analysis.
• Experimenting with agent-based and retrieval-based architectures.
• Translating complex code behaviour into meaningful, explainable insights.
• Experience in static code analysis is a strong advantage, but not mandatory. The primary focus is on AI/LLM engineering applied to privacy-aware code intelligence systems.

Education and Experience:

• Bachelor's or Master's degree in Computer Science, Engineering, or related field.
• Typically 3+ years of software engineering experience, with strong exposure to AI/ML or LLM-based systems.
• Candidates with experience in AI-driven developer tools, code intelligence systems, or data governance platforms are highly encouraged to apply.