AI Engineer

Job Summary

Plutus21 is looking for an AI Engineer to design, build and run AI-powered software systems that deliver practical value to the business and its clients. The role combines software engineering, product engineering and applied artificial intelligence, and uses AI to improve both how software is built and what it can do.

This is a hands-on engineering role, not a research or theoretical machine learning position, and it focuses on putting agentic systems and AI-enabled features into production. You will work with a high degree of autonomy, uses AI tools as part of everyday engineering work, and takes ownership of the systems in their area of responsibility.

Key Responsibilities

• Design, build and operate production software systems that include AI as a core capability.
• Build and integrate agentic systems that select tools, manage context and carry out multi-step tasks toward defined goals.
• Implement Model Context Protocol (MCP) or equivalent approaches to manage context, tools, memory and system boundaries in production.
• Translate product requirements into AI-enabled solutions that are scalable, reliable, secure and observable.
• Apply AI through prompting, orchestration, model composition, evaluation and deployment, with a focus on runtime behavior rather than model training.
• Treat model inputs, outputs and behavior as versioned and testable parts of the system.
• Use AI-assisted coding, engineering agents, AI-driven testing, debugging, refactoring and documentation as part of daily development work.
• Refine prompts, policies, agent flows and context inputs as a normal part of development to improve system behavior and outcomes.
• Improve AI-enabled development practices within assigned systems and team workflows to reduce manual effort and raise delivery quality.
• Work closely with product, delivery and engineering colleagues to deliver AI-powered features end to end, and lead projects as a single-person team when appropriate.
• Integrate AI systems with external services, APIs and data sources within production applications.
• Contribute to shared platforms, services and internal tools in line with established patterns and architectural direction.
• Balance fast iteration with sound engineering judgment and long-term maintainability.
• Take full ownership of the quality of deliverables across the stack, including building automated checks and AI agents that verify quality.
• Ensure AI-enabled systems meet enterprise standards for security, performance, reliability and compliance.
• Implement monitoring, safeguards and evaluation for AI behavior in production, including detection of hallucinations, regressions and unintended behavior.
• Treat evaluation, traceability and explainability as ongoing engineering responsibilities.
• Own assigned solutions from initial design through deployment and ongoing operation.
• Stay current on AI tools, platforms, models and agentic patterns relevant to production software.
• Test new AI capabilities responsibly and turn the results into concrete improvements in owned systems and workflows.
• Contribute to a culture of technical excellence, accountability and continuous learning.
• Perform other duties as assigned.

Qualifications

• Bachelor's degree in Computer Science, Engineering or a related technical field, or equivalent practical experience.
• Strong software engineering fundamentals and experience building and operating production systems.
• Hands-on experience building or working with agentic AI systems that select tools and carry out multi-step tasks.
• Experience using Model Context Protocol (MCP) or equivalent approaches to manage tools, context and memory in production AI systems.
• Sound technical understanding of AI models, including model versions, parameter sizes, context window limits, system and user prompts, and the latency, cost and reasoning trade-offs between models.
• Experience working with open-source AI models as well as commercial or hosted models.
• Experience integrating AI systems with external services, APIs and data sources.
• Ability to evaluate AI systems beyond accuracy, including reliability, hallucination risk, traceability and safety.
• Experience addressing scaling concerns such as latency, cost, caching, parallelization, and the trade-offs between retrieval-based approaches and fine-tuning.
• Proven ability to take AI systems from prototype to pilot to production, with awareness of common failure modes and how to mitigate them.
• Comfort working autonomously in small, highly empowered teams.
• Experience integrating frontier and open-source models into SaaS or enterprise applications is preferred.
• Familiarity with cloud-native architectures and modern development stacks is preferred.
• Experience in regulated, enterprise or mission-critical environments is preferred.
• Background in product-oriented engineering organizations is preferred.