Applied AI Engineer

Axiomatic AI • Boston, MA

23h • Hybrid

About The Position

Axiomatic AI is building AI systems that combine deep learning with formal logic and physics-based modeling to support human researchers in scientific and engineering workflows. The company’s 30×30 mission is to improve the speed, accessibility, and cost of semiconductor and photonic hardware development by 30 times by 2030.

The Applied AI Engineer will own the agent platform that enables AI agents to run scientific and engineering workflows reliably and safely, including in lab environments. As the main owner of the platform code on a small, cross-functional team, the engineer will scope their own work and make decisions about how the platform is built. The role covers platform design, implementation, releases, and support; converting research experiments into production features; and working with scientists to integrate their workflows into the product.

The role is hybrid, based at the company’s Boston office three days per week.

Requirements

• At least 5 years of software engineering experience, mostly at companies shipping software to real customers.
• At least 2 years building LLM features that run in production at a company, beyond prototypes.
• Strong Python skills, including packaging with uv or Poetry, type hints, async, testing, and building CLIs.
• Hands-on experience building or extending MCP servers and designing tools for LLM tool calling.
• Good working knowledge of current agent harnesses such as Claude Code, Codex, Cursor, or similar, including plugins, skills, hooks, subagents, MCP support, and their limitations; uses these tools daily.
• Working understanding of agent architecture, including how the model, harness, tools, and state fit together and which decisions belong in code rather than prompts.
• Experience evaluating LLM systems, including building test sets, catching regressions, and explaining results to others.
• A safety mindset, including human-in-the-loop approvals, code-based guardrails, audit logs, and awareness of prompt injection.
• Care for compatibility, including versioning, smooth upgrades, and installers that can be run twice without breaking anything.
• Experience with CI/CD using GitHub Actions and Docker.
• Comfort working in a small team with unclear requirements, scoping work independently, and shipping with little support.
• Clear, confident communication with technical and non-technical stakeholders, including constructive challenge or pushback when needed.
• Professional fluency in English.

Nice To Haves

• Experience running LLMs and software in restricted or customer-managed environments.
• Experience with Pydantic AI, LangGraph, or similar agent frameworks.
• Experience with lab automation, instrument control, or hardware connections such as VISA/SCPI or OpenTAP.
• Experience with observability tools such as OpenTelemetry, Logfire, or Sentry.
• Exposure to photonics or semiconductors.
• Open-source contributions to agent tooling.
• Research or academic experience is welcome, but should not be the candidate’s only background.

Responsibilities

• Own the agent platform end to end, including design, implementation, releases, and support.
• Design typed, tested tools for agents to plan, run, and verify work, and determine what belongs in a tool versus a prompt.
• Keep the platform portable and well documented so it is easy to adopt and extend.
• Build safety and traceability into the platform.
• Run evaluations that inform decisions, including golden task sets, baselines for every release, and comparisons across clients and models, including local models.
• Ship changes in small, reversible steps and provide upgrade paths that require no manual work from users.
• Turn research experiments into production features and work with scientists to bring their workflows into the product.
• Write ADRs and review code with the team.

Benefits

• Competitive compensation package.
• Stock options plan.
• Access to state-of-the-art tools and collaborative opportunities with experts in artificial intelligence, physics, hardware, and electronic design automation.
• Hybrid work arrangement with three days per week in the Boston office.
• Opportunities to attend industry conferences, present research findings, and engage with the global AI research community.
• Opportunity to contribute to AI for scientific and engineering applications and see research ideas commercialized into products.

What This Job Offers

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