Principal Engineer

Role Summary

We are seeking a hands-on Principal Engineer / Technical Lead to help scale a modern software platform through launch and into early growth. This role is designed for a senior technical leader who can combine architecture judgment, coding depth, AI engineering capability, and engineering discipline in a fast-moving SaaS environment.

We need a senior technical leader who can help the team ship quickly without allowing the platform to become fragile, inconsistent, or overly dependent on a small number of individuals.

This person will serve as a player-coach: contributing directly to difficult implementation work while also improving architecture adherence, code review quality, engineering standards, and team leverage.

This role also requires meaningful hands-on experience with AI-powered application development so the individual can help guide LLM- and agent-oriented architecture, support client-facing technical conversations, and reduce dependency on a single AI technical leader.

Key Responsibilities

* Partner with product and engineering leadership to drive technical delivery through launch and early scale

* Contribute hands-on to the codebase across critical areas of the platform, especially on complex or high-risk work

* Contribute hands-on to AI-powered platform capabilities, including LLM-integrated workflows, retrieval patterns, prompt orchestration, and agent-oriented application components

* Review architecture-significant pull requests and ensure code aligns with established patterns, boundaries, and long-term design direction

* Help define and enforce engineering standards for code quality, testing, review discipline, observability, and release readiness

* Help define practical architecture and engineering standards for AI application quality, evaluation, guardrails, observability, and production readiness

* Reduce key-person dependency by documenting design decisions, spreading architectural context, and mentoring other engineers

* Reduce concentrated AI architecture knowledge risk by documenting design decisions, sharing context broadly across the team, and mentoring engineers on effective AI implementation patterns.

* Improve the team’s use of AI-assisted coding and agentic development tools in a safe, disciplined, and repeatable way

* Help strengthen trust boundaries across authentication, authorization, tenant isolation, query execution, secrets handling, and cloud infrastructure

* Work closely with engineers across frontend, backend, AI orchestration, and infrastructure to unblock delivery and improve system cohesion

* Identify architectural hotspots, technical debt, and operational risks that could impair launch readiness or future scale

* Support the evolution of CI/CD, deployment confidence, and production-readiness practices

* Support technical solutioning discussions with clients and internal stakeholders for AI-driven use cases, translating implementation tradeoffs clearly and credibly

* Provide pragmatic technical leadership suited to a small, fast-moving company rather than a heavily layered enterprise environment

What Success Looks Like

* Within the first 90 days, this person will:

* Increase confidence in the architectural integrity of the codebase

* Improve the quality and rigor of PR reviews on critical-path changes

* Reduce dependence on a single technical linchpin for architecture and difficult implementation decisions

* Accelerate delivery on launch-critical work without sacrificing maintainability

* Help create a more scalable engineering operating model for a small but growing product team

* Establish practical standards for how the team uses AI coding tools and agentic workflows

* Increase confidence in the team’s ability to design and deliver AI-powered product capabilities without over-reliance on a single individual

* Establish practical architectural direction for LLM integration, retrieval/agent workflows, and AI feature delivery aligned with launch needs

* Demonstrate credible depth in AI engineering and technical solutioning in support of prospective client conversations and implementation planning

Required Qualifications

* 8+ years of software engineering experience, with substantial time spent in senior or principal-level hands-on roles

* Proven experience building and scaling SaaS platforms in production

* Strong full-stack engineering capability, with the ability to move between backend, frontend, and platform concerns as needed

* Strong architecture skills, especially in modular system design, service boundaries, shared patterns, and maintainability

* Experience operating in cloud-native environments and supporting production systems

* Experience with Python-based backend platforms, API-oriented architectures, and modern JavaScript frontend frameworks

* Strong code review judgment, with the ability to enforce standards while remaining pragmatic and delivery-oriented

* Experience with multi-tenant SaaS security and data isolation concerns

* Experience mentoring engineers and raising technical discipline on a small team

* Ability to critically review AI-assisted code contributions and establish team norms for responsible use of AI coding tools

* Ability to thrive in ambiguity and move fluidly between architecture, implementation, and technical problem-solving

* Excellent written and verbal communication skills, including the ability to explain tradeoffs clearly to both technical and non-technical stakeholders

* Hands-on experience building or integrating AI-powered software features or platforms in production, including LLM-enabled or workflow-driven application components

* Practical understanding of AI application architecture, including model integration patterns, retrieval workflows, prompt orchestration, evaluation, and guardrails

* Ability to represent the engineering team credibly in technical conversations involving AI use cases, implementation tradeoffs, and delivery considerations

Preferred Qualifications

* Experience with AI-powered products, LLM application development, agent orchestration, or natural-language-driven systems

* Experience with retrieval-augmented generation, semantic search, NL2SQL, or LLM query generation systems

* Experience integrating foundation model providers and managing AI application concerns such as latency, cost, quality, safety, and observability

* Experience with containerized cloud deployments in production; AWS familiarity preferred

* Experience defining engineering standards in early-stage or growth-stage product companies

* Hands-on experience with PostgreSQL in a production environment, including migrations, query optimization, connection pooling, and PostgreSQL-specific operational behaviors

* Practical experience using AI-assisted coding tools in a team setting

* Familiarity with agent orchestration frameworks such as LangChain, Agno, CrewAI, or equivalent orchestration patterns

Ideal Candidate Profile

The ideal candidate is not a pure architect and not just an individual contributor. This is a senior technical leader who still likes to build, can earn credibility through code, and knows when to zoom out to protect the system. They should bring both strong platform engineering judgment and meaningful AI engineering depth, with the ability to help shape LLM- and agent-oriented capabilities in a practical, production-minded way.

They should be able to look at a pull request and quickly determine whether it is merely functional or whether it truly fits the architecture, preserves the right boundaries, and sets the team up to move faster in the future.

They should be comfortable working in a startup-style environment where speed matters, resources are constrained, and good judgment is often more important than process overhead.

Reporting / Working Model

Reports to: CTO or Head of Engineering

Works closely with: product leadership, engineering team, QA, and platform/infrastructure stakeholders

Role type: Full-time or contract-to-hire, depending on business need and timing