Artificial Intelligence Engineer

Senior Software Engineer – Agentic AI & Distributed Systems

Location: San Francisco, CA (5 days onsite)

Employment Type: Full-time, Permanent

Compensation: $180,000–$330,000 base salary + competitive equity

Experience: 5–10 years preferred

Visa Sponsorship: Available, including H-1B transfers and new sponsorship applications

About the Company

We are partnering with a well-funded, early-stage AI technology company developing advanced autonomous systems designed to transform how engineers design, simulate, and develop complex physical products.

Backed by $32 million in venture capital funding, the company is building an AI-native platform that enables artificial intelligence agents to operate sophisticated desktop engineering applications, automate complex technical workflows, and significantly accelerate product development across industries including aerospace, automotive, and advanced manufacturing.

Rather than developing conventional AI assistants or standalone productivity tools, the company is creating intelligent software agents capable of interacting directly with professional engineering applications. These agents execute multi-step tasks across computer-aided design (CAD), computer-aided engineering (CAE), and product lifecycle management (PLM) systems.

The technology is designed to automate time-consuming engineering processes, improve design and simulation efficiency, and allow highly skilled engineers to focus on more complex technical and creative challenges.

The company has already established commercial traction, with thousands of users running production workflows and adoption among major global technology and engineering organisations.

With an experienced founding team, strong institutional backing, and an ambitious technical roadmap, the company is expanding its engineering organisation to accelerate the development of its core agentic AI infrastructure.

This is an opportunity to join a small, highly technical team at an early stage, contribute directly to the company's most important engineering challenges, and help define the next generation of AI-powered engineering automation.

The Opportunity

We are seeking an exceptional Senior Software Engineer – Agentic AI to join the company's core engineering team in San Francisco.

This position will focus on designing, building, and optimising the underlying systems that enable autonomous AI agents to execute complex, multi-step workflows across professional desktop engineering software.

You will report directly to the CTO and work closely with experienced software engineers, AI specialists, product stakeholders, researchers, and engineering domain experts.

The role combines advanced software engineering, agent orchestration, systems architecture, performance optimisation, and applied AI development.

You will be responsible for developing production-grade systems that enable AI agents to interact reliably with external applications, manage context and state across long-running operations, recover from failures, and execute technically demanding workflows with high accuracy and efficiency.

Unlike roles focused primarily on integrating third-party AI APIs or building conventional application features, this position involves engineering the foundational infrastructure that makes autonomous agents reliable, scalable, and commercially viable.

Success will be measured through tangible engineering outcomes, including agent task completion rates, execution reliability, latency, computational efficiency, and the breadth of workflows supported.

The company is particularly interested in engineers with exceptional computer science fundamentals, strong production engineering experience, and the ability to independently own complex technical systems.

Previous experience developing LLM agents is advantageous but not mandatory. Candidates with strong software engineering and systems design backgrounds who are genuinely interested in advancing agentic AI technology are strongly encouraged to apply.

Key Responsibilities

Agent Systems Engineering & Architecture

• Design, develop, and maintain the core infrastructure supporting autonomous AI agents capable of executing complex, multi-step engineering workflows.
• Build systems for agent orchestration, tool calling, state management, context handling, and intelligent model routing.
• Architect reliable execution mechanisms that maintain consistency and state across long-running operations involving multiple applications and external tools.
• Develop robust error detection, failure recovery, retry, and exception-handling capabilities to improve agent reliability.
• Design scalable software components capable of supporting concurrent agent execution and complex workflow dependencies.
• Build and maintain production systems that interact directly with desktop engineering applications and enterprise software environments.
• Make architectural decisions concerning performance, system reliability, scalability, maintainability, and operational complexity.
• Take end-to-end ownership of critical engineering components, from initial design and implementation through deployment, monitoring, and continuous improvement.

AI Infrastructure & Performance Optimisation

• Develop and optimise infrastructure supporting the execution of LLM-powered agents in production environments.
• Implement efficient context management strategies to support complex, multi-step tasks while controlling computational overhead.
• Design and improve model selection and routing mechanisms based on task complexity, performance, and cost requirements.
• Profile and optimise system latency, execution time, and resource consumption across agent workflows.
• Develop mechanisms for monitoring token usage, enforcing execution budgets, and tracking the cost of completed tasks.
• Identify and resolve performance bottlenecks affecting agent throughput, reliability, and responsiveness.
• Collaborate with AI engineers to improve the integration of language models, tools, and orchestration systems.
• Ensure that AI systems are engineered for production reliability and commercial efficiency rather than experimental performance alone.

Agent Evaluation, Testing & Reliability

• Design and develop evaluation frameworks to measure the effectiveness and reliability of autonomous agents.
• Create reproducible benchmarks that assess real-world engineering workflows rather than relying exclusively on synthetic test scenarios.
• Translate validated engineering use cases into structured evaluation datasets, test cases, and performance benchmarks.
• Develop automated testing infrastructure to measure task completion rates, execution accuracy, failure patterns, and workflow coverage.
• Implement monitoring and observability systems that provide visibility into agent behaviour and production performance.
• Identify recurring failure modes and systematically improve the agent's ability to recover from errors and complete complex tasks.
• Work with researchers and engineering domain experts to develop increasingly challenging evaluation scenarios.
• Establish measurable standards for agent performance and contribute to continuous improvements in reliability and capability.

Desktop Software Integration & Enterprise Systems

• Develop production software that enables AI agents to interact programmatically with complex desktop engineering applications.
• Build reliable integration mechanisms for CAD, CAE, PLM, and other specialised enterprise software environments.
• Address technical challenges associated with application control, workflow execution, asynchronous operations, and software interoperability.
• Design systems capable of operating within enterprise environments with strict security, access, and deployment constraints.
• Ensure that agent functionality remains robust when interacting with legacy applications, constrained workstations, and complex software dependencies.
• Collaborate with integration engineers to define the capabilities, interfaces, and tools required to support additional engineering applications.
• Improve the reliability and maintainability of application integration layers as platform capabilities expand.

Product Engineering & Cross-Functional Collaboration

• Work closely with product teams, user researchers, and domain specialists to understand how professional engineers perform complex technical workflows.
• Translate real-world engineering requirements into reliable software architectures and production-ready agent capabilities.
• Collaborate with customers during proof-of-concept implementations to understand product performance and identify areas for improvement.
• Contribute to technical discussions concerning product capabilities, engineering priorities, and system design trade-offs.
• Independently scope, prioritise, develop, and deliver complex technical initiatives.
• Participate in architectural reviews, code reviews, and technical planning to maintain high engineering standards.
• Help establish engineering best practices, development processes, and technical standards within a growing startup environment.

Required Qualifications

• 5+ years of professional software engineering experience preferred, with demonstrated success building, shipping, and maintaining production systems. Exceptional candidates with 3–4 years of particularly strong experience may also be considered.
• Excellent computer science fundamentals, including data structures, algorithms, software architecture, concurrency, and systems design.
• Strong programming experience in Python, alongside proficiency in at least one additional programming language.
• Demonstrated ability to design, implement, and maintain complex software systems in production.
• Strong understanding of software engineering principles, including modular design, abstraction, performance optimisation, debugging, and maintainability.
• Experience solving technically challenging problems involving system reliability, complex workflows, state management, or application integration.
• Ability to design scalable systems and clearly explain architectural decisions, technical constraints, and engineering trade-offs.
• Experience implementing robust testing strategies and diagnosing complex production issues.
• Proven ability to take ownership of substantial engineering projects from technical design through implementation, deployment, and maintenance.
• Strong analytical and problem-solving abilities, with the capacity to work through unfamiliar technical challenges independently.
• Evidence of sustained technical contribution, increasing engineering responsibility, and meaningful ownership of production systems.
• Excellent communication skills and the ability to collaborate effectively with engineers, researchers, product stakeholders, and technical customers.
• Genuine interest in AI agents, autonomous systems, and the application of artificial intelligence to complex real-world engineering problems.
• A proactive, highly autonomous working style and enthusiasm for operating within a fast-moving, technically demanding startup environment.
• Ability and willingness to work onsite in San Francisco five days per week.

We are particularly interested in candidates who have demonstrated exceptional technical depth, strong engineering judgment, and the ability to solve complex systems problems independently.

A strong foundation in software engineering is more important than prior experience with any specific AI framework or agent technology.

Preferred Qualifications

The following experience would be advantageous but is not mandatory:

• Previous experience as a Senior Software Engineer, Staff Software Engineer, AI Infrastructure Engineer, Systems Engineer, or Agentic AI Engineer.
• Experience at high-growth technology startups, AI-native software companies, or organisations with a strong engineering culture.
• A track record of designing and owning complex technical systems from the ground up.
• Experience building LLM-powered applications, autonomous agents, or agent orchestration frameworks.
• Familiarity with tool calling, context management, agent memory, model routing, and multi-step workflow execution.
• Experience developing evaluation infrastructure, automated benchmarks, or performance testing frameworks for AI systems.
• Strong understanding of distributed systems, asynchronous programming, concurrency, fault tolerance, and failure recovery.
• Experience with production observability, performance profiling, and application monitoring tools.
• Familiarity with LangSmith, Logfire, or comparable AI observability and evaluation platforms.
• Experience with desktop application automation, Windows COM interfaces, or programmatic control of external software.
• Experience developing software for enterprise environments with complex deployment, security, or infrastructure constraints.
• Familiarity with CAD, CAE, PLM, simulation software, or other technical engineering applications.
• Experience working directly with customers to translate complex operational requirements into software solutions.
• A strong academic background in computer science, software engineering, or a related technical discipline.

Previous experience in mechanical engineering, CAD/CAE applications, or hardware development is not required. The company prioritises exceptional engineering fundamentals, technical versatility, intellectual curiosity, and a demonstrated ability to learn challenging new domains.

Likewise, prior professional experience developing AI agents is not essential for candidates who can demonstrate substantial software engineering depth and a strong interest in the field.

Technology Environment

The engineering team works across an advanced AI and software engineering technology environment that includes:

• Primary Programming Language: Python
• AI & Agentic Systems: Large Language Models (LLMs), autonomous AI agents, tool calling, model routing, context management, and multi-step workflow orchestration
• Observability & Evaluation: LangSmith, Logfire, agent evaluation frameworks, performance monitoring, and benchmark infrastructure
• Backend & Systems Engineering: Asynchronous programming, concurrency, state management, failure recovery, reliable execution, and production systems architecture
• Desktop Software & Integration: Windows COM, desktop application automation, enterprise software integration, and programmatic application control
• Engineering Applications: Computer-Aided Design (CAD), Computer-Aided Engineering (CAE), Product Lifecycle Management (PLM), and simulation software
• Core Engineering Challenges: Agent task reliability, execution latency, token efficiency, context optimisation, workflow coverage, and robust automation across complex desktop environments

Candidates are not expected to have experience with every technology listed. Strong computer science fundamentals, proven production engineering experience, and the ability to work effectively across technically complex systems are more important than exact technology alignment.