Software Engineer – Agentic Platform

Most engineers who use AI tools are operators: they prompt an agent, review the output, and ship the result. This role is different. You're not just using the pipeline – you're building it.

Nectar and Vivery are platforms that connect people facing food insecurity with community organizations and the wraparound support they need. We're a small team moving fast, and we've built an agentic build pipeline – a system of orchestrated AI coding agents, evaluation harnesses, guardrails, and feedback loops – that lets us build and operate software at a pace a traditional team our size couldn't match. That pipeline is how we're building Nectar 2.0, an agentic platform where AI is the primary author of new code.

This role works in close collaboration with our CTO, who sets technical direction. You'll extend and strengthen the pipeline itself, build full-stack features across both platforms, and carry real production ownership for what you ship. This is a you-build-it-you-run-it team. The work is underway now, and you'll be stepping into it, not starting from scratch.

If you're the kind of engineer who wants to understand systems at every level, who'd rather design the machinery than just operate it, and who's energized by work that has a direct impact on real people – this is a rare seat.

Why This Matters

Nectar connects food-insecure Neighbors with food pantries, nutrition programs, benefits and community-based organizations. The code you ship is the connective tissue between healthcare systems, community food networks, and the neighbors they both serve.

When the pipeline produces bad output and it reaches production, real people are affected. That's not a reason to be slow – it's a reason to build the right guardrails, design for blast radius, and take production ownership seriously. The engineers here care about that standard because of what's on the other end, not because a process document says to.

What You'll Do

Build and extend the agentic build pipeline

• Design and maintain the orchestration layer: the pipelines, agent configurations, evaluation harnesses, guardrails, and feedback loops that let AI coding agents produce real, deployable software reliably and at scale.
• Go beyond prompting. This work is about building the machinery around AI agents – the systems that catch failures, validate output, and keep the pipeline trustworthy even when an individual agent isn't.
• Establish and refine the patterns that make a heavily AI-authored codebase something the whole team can build on, review, and trust in production.

Develop full-stack features across Nectar and Vivery

• Build and ship end-to-end features across both platforms, from database to API to UI.
• Work across the stack without strong language preference. The right tool for the problem matters more than a favorite language.
• Collaborate closely with the engineering lead on architecture decisions, with the autonomy to drive implementation without the path being laid out step by step.

Own automation across development and operations

• Build and maintain CI/CD, infrastructure tooling, and internal automation wherever it removes toil and accelerates the team.
• Treat the pipeline itself as a production system: monitored, instrumented, and owned.
• When something breaks, you're in the rotation. On-call ownership is part of the role for the systems you build.

Design for the real world, not the ideal one

• Ship solutions that limit blast radius when something goes wrong, rather than chasing perfection that arrives too late.
• Know how to contain a failure, roll back cleanly, and learn from it faster than a traditional team could.
• Bring a pragmatic view of risk: what's safe to ship now, what needs more runway, and why.

What This Role Is Not

• Not an AI prompt engineer. Skilled use of AI coding tools is table stakes here, not the job. The job is building the systems around those tools.
• Not a single-stack specialist. Engineers who want to work in one language or one layer of the stack are not a fit. Full-stack means full-stack.
• Not a feature factory contributor. You're not filling a backlog someone else owns. You're making architectural decisions, carrying production responsibility, and helping define how this team builds software.
• Not a corporate engineer. There's no process scaffolding here to feel safe inside. You'll help create the process that's actually worth having – and you'll be comfortable until it exists.

What Success Looks Like

90 Days

• You're shipping. Real features are in production on Nectar or Vivery, built and owned by you.
• You understand the agentic build pipeline end to end: where it's strong, where it's fragile, and what needs work.
• At least one improvement to pipeline reliability or evaluation coverage is in production.
• You're in the on-call rotation for systems you've built, and you've handled something that went wrong.

6 Months

• The pipeline is measurably more reliable than when you arrived. Guardrails and evaluation harnesses are stronger.
• Nectar 2.0 development patterns are established and the team builds on them with confidence.
• You've made at least one architectural decision that the team adopted, and can articulate why.
• Toil is down. Automation you built is doing work that used to require a human.

12+ Months

• The agentic build pipeline is a genuine multiplier: the team ships at a pace that wouldn't be possible without it, and it's trustworthy enough to stake production on.
• Nectar 2.0's AI-authored codebase is something any engineer on the team can navigate, extend, and own.
• You've helped define how this team builds software at scale – and that definition has evolved as the platform has grown.

What We're Looking For

Engineering depth first

• Deep command of software fundamentals at every level: network behavior, how a database actually stores a row, what happens between a browser request and a rendered response.
• The instinct to reach for the right tool for the problem, not a single preferred language. Broad fluency matters more than depth in one stack.
• The ability to analyze a vague or partial requirement, find the real problem beneath it, and design a solution without the path being laid out.

A clear-eyed view of AI tools

• Daily, practical fluency with AI coding tools – not as a novelty, but as actual leverage you've built work habits around.
• A real understanding of where these tools fail and why, and more importantly, the ability to build systems around those failure modes so the pipeline stays reliable even when an individual agent isn't.
• No illusions about AI as a magic output machine. You've seen it produce confident nonsense and you know how to catch it.

Independence and collaboration in equal measure

• You can take ambiguous direction, make reasonable assumptions, and ship – without going dark for weeks and resurfacing with something nobody asked for.
• You work closely with the team, share context early, and flag blockers before they become problems.
• You have opinions about how things should be built, you argue for them, and you move on once a decision is made.

A startup temperament

• Bias toward action. Comfort in ambiguity. No need for a process to feel safe – and the judgment to help create the process that's actually worth having.
• Pragmatism about risk: how to ship something imperfect safely, contain failures, and roll back cleanly.
• A sense of ownership that doesn't stop at the edge of your ticket.

Background We're Looking For

We care more about how you think and build than where you've been. That said, relevant experience includes:

• Strong full-stack engineering background with production ownership experience
• Hands-on work building automation, CI/CD pipelines, or developer tooling – not just using them
• Practical experience with LLM and agentic coding tools in a real development workflow
• Experience designing or operating AI-assisted development pipelines, evaluation harnesses, or similar systems is a strong plus
• Comfort with distributed systems, cloud infrastructure, and the operational realities of production software

Why This Role Is Worth It

It's 2026. Most engineering teams are still figuring out how to use AI tools responsibly. Nectar has already built the pipeline and is using it to build production software. The engineer in this role isn't experimenting with the future – they're operating in it, and helping define what it looks like to build trustworthy AI-authored software at scale.

This is a small team, which means the work you do is visible, the decisions you make matter, and the impact on the people who use these platforms is direct. You won't be a contributor to a roadmap someone else owns. You'll be one of the people who built it.

We're building something the charitable food and healthcare systems have been waiting for. Come help us build it right.

About Nectar & Vivery

Nectar is an AI-enabled platform connecting food-insecure neighbors, food banks, and Managed Care Organizations (MCOs) for Food is Medicine programs. Vivery is the community-facing brand – the platform that neighbors, food pantries, and community-based organizations use to find and provide support.

Together they sit at the intersection of healthcare and community food networks, built on a five-year foundation of 25,000+ community-based organizations and food pantries across the country. We are a small, mission-driven team building ambitious technology with real impact – and we believe that food is the highest-frequency engagement vector in health.

Work Environment

This role is based in Chicago, and candidates must be able to work from our office in River North, 2-3 days per week, or as needed.

Compensation & Benefits

$150K - $185K annually, plus equity participation. Final compensation will be determined based on experience and qualifications.

Benefit Package Includes:

• Medical, dental, and vision benefits
• 15 days PTO, 10+ paid holidays, and 10 days paid sick leave
• 401(k) with partial company match
• Voluntary long-term disability and life insurance

To apply: submit your resume via LinkedIn or to [email protected]. No recruiters, please.