Senior Applied AI Engineer

Axiomatic AI • Boston, MA

3d • Hybrid

About The Position

Axiomatic AI is building AI systems that combine deep learning with formal logic and physics-based modeling to create verifiable, interpretable systems for scientific and engineering workflows. Its mission is to improve the speed, accessibility, and cost of semiconductor and photonic hardware development by 30 times by 2030.

The Senior Applied AI Engineer bridges AI research and production software. The role partners with users and internal stakeholders to identify valuable AI workflows, designs and ships LLM-powered product features, and makes informed trade-offs among model quality, latency, cost, privacy, and reliability. The engineer establishes practices that help AI developers deploy work reproducibly and safely, works with backend engineers to integrate AI capabilities, mentors AI developers, and monitors and improves AI and agentic workflows.

The position owns applied AI features end to end, from discovery and design through implementation, rollout, and iteration. It includes building tool-calling agents, structured-output pipelines, retrieval and tool integrations, and safe prompting strategies; selecting and evaluating models; developing prompts and guardrails; and running evaluations to prevent regressions. The engineer writes production-grade code, defines testing practices, adds debugging instrumentation, and addresses reliability and security basics. They also help productionize AI developers’ experiments, document infrastructure and best practices, review code, and communicate technical decisions clearly to colleagues and stakeholders.

The role is hybrid, based at the Boston office, with an expectation to work there three days per week. The company offers flexible work arrangements and potential remote-work options.

Requirements

• At least 7 years of software engineering experience, preferably with Python, and strong production ownership.
• Experience with LLMs and AI/ML in production, such as OpenAI API, HuggingFace, LangChain, or similar, beyond prototypes.
• Strong software engineering fundamentals, including design patterns, code structure, testing practices, and code review habits.
• Cloud infrastructure experience with GCP, preferably Vertex AI, or AWS, including SageMaker.
• API and service development experience, such as FastAPI, REST, or asynchronous programming.
• Experience with CI/CD and DevOps tools, including Docker, Terraform, and GitHub Actions.
• Experience with monitoring and observability.
• Operating experience deploying AI in an enterprise environment.
• Experience shipping data projects to real users.
• Experience collaborating with software engineers.
• Problem-solving mindset.
• Proactiveness and versatility, including comfort independently defining and scoping tasks and taking initiative to find improvements.
• Ability to communicate technical concepts and justify decisions precisely and concisely.

Nice To Haves

• Experience fine-tuning or training models.
• Familiarity with LangChain, Pydantic AI, or similar frameworks.
• Knowledge of prompt engineering and evaluation techniques.
• Experience with real-time inference and streaming responses.
• Background in data engineering or ML engineering.
• Understanding of RAG architectures.
• Contributions to open-source AI/ML projects.

Responsibilities

• Partner with users and internal stakeholders to identify high-impact workflows where AI can help.
• Own applied AI features end to end, from discovery and design through implementation, rollout, and iteration.
• Translate user feedback and behavior into technical requirements and delivery plans.
• Build LLM workflows, including tool-calling agents, structured-output pipelines, retrieval and tool integrations, and safe prompting strategies.
• Select and evaluate LLMs according to quality, cost, latency, context limits, and reliability.
• Develop prompt patterns and guardrails, and design lightweight evaluations to prevent regressions.
• Document model decisions and trade-offs so other engineers can execute confidently.
• Write production-grade code with clear abstractions, sound API boundaries, appropriate strong typing, and consistent error handling.
• Define and enforce applied AI testing practices, including unit, integration, golden, and regression tests.
• Implement logging, tracing, and metrics appropriate for debugging and iteration.
• Address reliability and security needs, including rate limiting where needed, safe input handling, prompt-injection awareness, and sensible defaults.
• Enable AI developers to deploy their work reproducibly and safely, and help productionize their experiments to improve user workflows.
• Define workflows from notebook and test repositories through pull requests and staging to production.
• Document AI infrastructure and best practices.
• Review code, supervise pull requests, and mentor AI developers on software practices.
• Collaborate with backend engineers to integrate AI capabilities into the product.
• Monitor, evaluate, and optimize AI and agentic workflows.
• Collaborate with specialists and scientists to bring their expertise into the AI product.
• Precisely and concisely explain and justify technical decisions to colleagues and stakeholders.

Benefits

• Competitive compensation.
• Stock Options Plan.
• Access to state-of-the-art tools and collaborative opportunities with experts in artificial intelligence, physics, hardware, and electronic design automation.
• Flexible work arrangements and potential options for remote work.
• Opportunities to attend industry conferences, present research findings, and engage with the global AI research community.
• Opportunity to work on impactful AI and hardware challenges with a passionate team.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed