Staff Engineer — Agentic AI

Praxy; San Francisco, Northern (CA, KY); Hybrid; USD 160,000 - 250,000; Full time

Job summary

Praxy is seeking a senior technical leader to own the core agent intelligence layer in an AI-native engineering software environment. You will report to the CTO and lead a small team of AI engineers, a user researcher, and contractors, shaping real-world product value for enterprise customers.

You will drive the full product loop from user story definition to implementation and benchmarking across CAD/CAE/PLM workflows, optimize costs, and ensure reliable multi-step automation in desktop

Qualifications

• 7+ years in software engineering with real-world agentic LLM systems.
• Deep experience with LLM architecture: model selection, context/window management, retrieval strategies.
• Strong evaluation and benchmarking instincts for agentic systems.
• Proven track record of shipped AI systems with measurable outcomes.
• Strong Python skills and hands-on familiarity with LLM tooling.
• Technical leadership experience for small teams (3–6 engineers).
• Hands-on background with mechanical engineering software (CAD/CAE/PLM).
• Experience shipping AI tooling on engineering data or desktop apps.

Responsibilities

• Lead development of the agent intelligence layer across CAD/PLM software.
• Own the full product loop from user story to implementation and benchmarking.
• Define evaluation frameworks and cost controls for per-task budgets and workflows.
• Collaborate with cross-functional teams during POCs to align agent behavior with real-world usage.
• Write production code, review designs, and raise the engineering bar.
• Architect tool-calling strategies, context management, and recovery for reliable workflows.

Skills

7+ years software engineering

Agentic LLM systems

Python skills

LLM tooling familiarity

Technical leadership

Desktop engineering tools

Cost optimization

Tools

Function calling

Tool use APIs

Tracing/observability

Evaluation frameworks

Job description

This is a senior technical leadership role at the heart of an AI-native engineering software company, owning the core agent intelligence layer that turns mechanical engineers' intent into reliable, cost-efficient multi-step workflows across complex desktop engineering tools. You'll report directly to the CTO and serve as the technical lead for a small team of AI engineers, a user researcher, and domain expert contractors. The work you do here will define real-world product value for enterprise customers.

WHAT YOU'LL DO

• Lead development of the agent intelligence layer that executes multi-step workflows across CAD, simulation, and PLM software.
• Own the full product loop — from user story definition to implementation to benchmarking against real engineering workflows.
• Drive agent task success rate by defining evaluation frameworks, establishing baselines, and iterating on performance.
• Set and enforce per-task token budgets and track cost per completed workflow to ensure commercial viability.
• Design rigorous, reproducible evaluation infrastructure grounded in validated user stories — think SWE-bench-level rigor applied to engineering workflows.
• Lead user story mapping and validation through direct interviews and collaboration with domain experts.
• Translate validated user stories into testable evals, closing the loop between user research and benchmarking.
• Own agent architecture decisions: tool-calling strategies, state management, error recovery, model routing, and context management.
• Act as a player-coach — write production code, review designs, unblock the team, and raise the engineering bar.
• Collaborate cross-functionally with integrations, product, and customers during POCs to align agent behavior with real-world usage.

WHAT WE'RE LOOKING FOR

• 7+ years in software engineering, including at least 2 years building and shipping real-world agentic LLM systems (tool calling, multi-step workflows, failure recovery, cost control).
• Deep experience with LLM application architecture: model selection, context/window management, retrieval strategies, tool-calling frameworks, and orchestration patterns.
• Strong evaluation and benchmarking instincts for agentic systems — task completion rates, cost efficiency, failure mode analysis; familiarity with benchmarks such as SWE-bench, GAIA, or τ-bench is a plus.
• Proven track record of shipped AI systems with measurable outcomes — not just demos or prototypes.
• Strong Python skills and hands‑on familiarity with the LLM tooling ecosystem (function calling, tool use APIs, tracing/observability tools, evaluation frameworks).
• Technical leadership experience setting direction for small teams (3–6 engineers) and performing meaningful code review and architecture decisions.
• Hands‑on background with mechanical engineering software — CAD/CAE/PLM or simulation tooling (e.g. Siemens NX/NXOpen, Teamcenter, CATIA, Creo, SolidWorks, Ansys, Abaqus, or similar) — either as a builder of these tools or as a power user inside an engineering or manufacturing org.
• Experience shipping AI/LLM tooling on top of proprietary engineering data or desktop engineering software (e.g. an agent or MCP server over CAD/PLM APIs, RAG over engineering repos or schematics).
• Familiarity with enterprise deployment constraints, including behavior on locked-down corporate workstations.
• Experience with desktop automation or programmatic control of applications (COM or similar) is a strong plus.
• Published work, open-source contributions, or benchmark contributions in agentic AI is a plus.

COMPENSATION & BENEFITS

Salary range: $160,000 – $250,000 USD annually. Visa sponsorship is not available for this role.

LOCATION

On-site in San Francisco, California, USA.

Pay

COMPENSATION & BENEFITS Salary range: $160,000 – $250,000 USD