Backend & Applied AI Software Engineer

Levanta Labs is the data engineering, software development, and AI partner for high-growth B2B companies & SaaS startups. We design, build, and scale custom software platforms, internal systems, and AI solutions that drive measurable operational and financial impact.

You'll be the engineer who builds the foundations of everything we ship - the services, data pipelines, and AI systems that power our clients' platforms, internal tools, and production agents. You'll work closely with frontend engineers, product stakeholders, and founders from the earliest stages of a project, helping shape how systems are architected and how AI actually lands in the real world. From multi-agent workflows and context management systems to retrieval pipelines, knowledge graphs, and self-learning memory architectures that improve over time, the engineering problems here excite us every single day.

The systems you'll build are high-stakes, production-grade platforms that client teams rely on. We're looking for engineers who can ship conventional backend software at a high standard and go deep on the emerging AI/agent ecosystem, architecting and deploying real solutions that hold up in production.

Roles & Responsibilities

* Design, build, and maintain backend services, production APIs, and core platform infrastructure

* Build and support internal tools and client-facing SaaS products end-to-end

* Develop data pipelines and backend workflows that move and transform data reliably

* Own backend architecture decisions with a focus on scalability, reliability, and maintainability

* Build and maintain cloud infrastructure and deployment pipelines (AWS preferred)

* Collaborate closely with frontend engineers, product stakeholders, and leadership to translate business needs into technical execution

* Design database schemas and data models that support high performance and scale cleanly as usage grows

* Ship performant agent workflows, tools, and context management systems that run real business operations

* Build context management systems (retrieval pipelines, vector search, knowledge graphs) that supply agents with relevant information

* Design ontologies and architectures for storing and retrieving reasoning traces, decision precedents, and reusable logic patterns

* Build self-learning memory systems that improve agent/tool recommendations over time

* Support unified dashboards with real-time visibility into operations (by powering the backend systems and data flows behind them)

* Write clean, testable, well-documented code and contribute to engineering best practices

* Take ownership of features and systems end-to-end: design → build → deploy → iterate

What You Offer (Requirements)

* 3+ years of backend engineering experience

* Strong proficiency in both Python and JavaScript/TypeScript

* Experience building and maintaining production APIs and services

* Understanding of at least one AI agent framework (e.g., LangGraph, Mastra, or similar)

* Familiarity with vector databases

* Comfort with cloud infrastructure (AWS preferred)

* Broad understanding of the AI/LLM ecosystem — not just “OpenAI API calls”

Nice to Have

* Experience with graph-based knowledge systems

* Background building systems that learn/adapt from usage patterns

* Exposure to workflow automation or process mapping

* CS degree or equivalent practical experience

Tech Stack

Python, JavaScript/TypeScript, Node.js, Express.js, PostgreSQL, MongoDB, Redis, AWS

What Success Looks Like

* You consistently ship reliable, production-grade backend systems that are stable, scalable, and maintainable

* APIs, pipelines, and services run cleanly in production with strong observability, low incident frequency, and fast resolution when issues arise

* You deliver high-quality work quickly, balancing speed with sound architecture and pragmatic tradeoffs

* AI systems you build are real, deployed, and operational - not prototypes - and they materially improve how clients run their business

* You proactively identify bottlenecks, edge cases, and risks before they become problems

* You collaborate smoothly across engineering and with stakeholders to keep projects moving and outcomes strong

What We Offer

* Fully remote role (Canada) — core hours 9am–6pm EST.

* Work on genuinely interesting AI transformation projects

* Mentorship from experienced engineers

* Exposure to a wide variety of industries and problem spaces

* Professional development resources

* Performance bonuses tied to project outcomes

* Clear growth path into a Technical Lead role with greater ownership and incentives.

* Gym membership stipend.

* Flexible paid time off.

* Direct collaboration with founders and a world-class technical team.

Work Environment

As a remote-first company, Levanta Labs is built for high performance and flexibility. We collaborate through Slack, Linear, Asana, Google Workspace, and Loom, maintaining a fast-paced but structured operating rhythm.

Equal Opportunity

Levanta Labs is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all team members. All qualified applicants will receive consideration without regard to race, color, religion, gender, gender identity, sexual orientation, national origin, disability, or veteran status.