Software Engineer
Employees are confused about their benefits, and the leaders funding that second-largest expense often can't tell what's working. Avante is changing that: We're an AI-native benefits intelligence platform already trusted by brands like Samsung, News Corp, and Zscaler, with two purpose-built agents. Carly gives employees personalized, always-on guidance, and Ava gives benefits leaders analyst-grade answers on cost, utilization, and outcomes in seconds, closing the loop between employee experience and strategy.
The Role
As a Software Engineer at Avante, you will design and build production systems across our TypeScript stack, increasingly directing AI agents to handle implementation while you own the architecture, correctness, and quality of what ships. This is a hands-on engineering role: you will solve real technical problems, ship features, and make pragmatic decisions that balance speed with maintainability. Your judgment about when to build directly and when to guide an agent will shape work that reaches Avante's enterprise customers directly.
What You'll Do
AI-Native Engineering
- Build and extend the AI infrastructure behind Carly and Ava, including prompt engineering, context management, agent orchestration, and reliable AI system integration
- Use AI coding tools (Claude Code, Cursor, or similar) as a core part of how you ship, with sharp judgment about where they accelerate work and where they fall short
- Increasingly direct AI agents to handle implementation, staying responsible for the architecture, correctness, and quality of what ships
- Help decide when and how AI agents get used as part of technical decision-making
Product & Customer Impact
- Collaborate closely with product, design, and engineering peers to deliver solutions that drive real business value, with a clear point of view on what's actually right for the customer
- Participate in design discussions and code reviews
Ownership & Execution
- Own outcomes across our TypeScript backend services and APIs, writing production code yourself
- Design, build, and maintain scalable services within our TypeScript monorepo, as we move toward a "touchless PR" model where agents handle more of the mechanical implementation and engineers focus on the judgment calls
- Model data, design schemas, and optimize queries in PostgreSQL
- Integrate with external systems including HRIS platforms, ticketing systems, and third-party APIs
- Build for production with attention to observability, monitoring, and testability from day one
What We're Looking For
- 3+ years of professional software engineering experience, primarily in backend development
- Strong proficiency in TypeScript or willingness to ramp quickly if coming from similar languages (Java, C#, Python)
- Solid experience with relational databases: schema design, query writing, and performance basics
- Familiarity with API design patterns and building services that other systems depend on
- Active engagement with AI engineering: hands-on experience with LLM APIs, agent workflows, or AI-assisted development, plus a real point of view on how AI is changing what a strong engineer owns and how they work. Self-directed exploration outside of work counts as much as production usage
- Demonstrated product and customer judgment: a track record of decisions that weigh what's technically correct against what's actually right for the end user
- Startup or high-ownership experience: comfort operating without a large team or established process behind you, and a bias toward shipping and iterating over waiting for a long spec
- Ability to work effectively in ambiguity and balance speed with maintainability
- Strong communication skills and genuine interest in understanding the problems you're solving
- Initial screen with our recruiters
- Video Interview with our Engineering Manager
- Technical interview focused on real-world problem solving (no whiteboard algorithms)
- On-site interview loop:
- Team behavioral interview (60 min)
- Session with our Engineering Manager (60 min)
- Final conversation with our CTO (30 min)
How We Work
Our four values aren't aspirational. They translate into concrete operating tenets that shape how we make decisions every day.
Beat Yesterday. We re-evaluate our own toolkit every quarter, because the workflows that made you effective three months ago may already be outdated. We act on 70% of the information rather than waiting for certainty. We timebox, execute, and iterate, getting work in front of real people quickly instead of polishing in isolation. And we own our output regardless of how we produced it. AI can get you 80% of the way there. Everything that goes out with your name on it is your responsibility to review, refine, and stand behind.
Embrace Type 2 Fun. We take on hard problems and find meaning in the work, even when it's uncomfortable. We assume good intent and follow up directly rather than venting in side channels. We celebrate wins loudly and specifically, naming the actual behavior so the whole team learns what great looks like. We are on by default, because we owe it to each other and to our customers to be available beyond what a regular corporate job would demand. And we do unscalable things today that build scalable advantages tomorrow: every hand-built account play and late-night proposal turnaround earns us the right to scale later.
Stay Hungry, Stay Curious. We expect everyone to be the expert on AI in their function before anyone asks them to be. The landscape changes weekly. When you learn something, teach it. Learn enough about adjacent functions to ask good questions. Ask the question you think is too basic, because in complex domains like benefits, the cost of a wrong assumption can be a lost account. And remember: curiosity without urgency is a hobby. Learning has to translate into action on a timeline that matches the opportunity.
Act Like an Owner. We say the uncomfortable thing early, raising missed commitments or quality gaps directly with the person within 48 hours. We surface problems when they're small, not the week they become a crisis. Customer-facing work gets priority, always. And we close the loop every time, because over-communication is a feature at our stage, not a bug.
Apply for this job
*
indicates a required field