Want to know if this job is worth applying to?
San Francisco, California, United States
Onsite
Unify is building the first AI-native outbound platform where agents and sellers work side by side. We help revenue teams identify buyers already in market, enrich accounts with data from 40+ sources, and execute personalized, multi-channel outreach—all from a single AI-powered workspace.
Trusted by some of the most innovative go-to-market teams, Unify enables reps to spend less time on manual work and more time building relationships, delivering up to 90% time savings on list building and 19% higher output per rep.
We're building a team of curious, ambitious people who care deeply about craftsmanship, move with urgency, and thrive in fast-paced environments. If you're excited about shaping the future of AI and building products that redefine how modern revenue teams work, we'd love to meet you.
As an Applied AI Engineer at Unify, you will bring new agent capabilities from zero to one and build the systems that make them work in production. You’ll own the agent harnesses that turn model capabilities into useful actions: planning, tool execution, context management, memory, and error recovery.
You will work closely with product, design, and engineering to build agents that research accounts, identify opportunities, and execute GTM workflows. You’ll move quickly from prototype to customer usage, then use evaluations and real execution traces to make the product better. If you want to build production AI systems and own the outcome from first experiment through launch, this role is for you.
Build agent harnesses: Design the execution loops, tool interfaces, context, and memory that let agents complete complex workflows reliably.
Ship AI products end to end: Turn ambiguous customer problems into working features, connecting agents to Unify’s data, integrations, and workflow infrastructure.
Make quality measurable: Build evals from real customer tasks, and use traces and failure analysis to improve agent behavior.
Build for production: Own reliability, latency, and cost. Make long-running tasks resumable, handle tool failures, and give users visibility and control over agent actions.
Experiment with new capabilities: Test models, prompting strategies, retrieval approaches, and orchestration patterns. Measure what improves outcomes and bring it into the product.
Shape our AI foundation: Build reusable tools and engineering practices that help the team ship faster, partnering with product and design to prioritize the work that matters most to customers.
You have 3+ years of software engineering experience and hands-on experience shipping LLM applications or agents to production.
You have built systems with tool calling, multi-step execution, and evaluations. You understand how the software around a model affects what it can accomplish.
You are a strong programmer in TypeScript or Python, with experience building backend systems and integrating APIs. You’re comfortable owning a feature across the stack.
You think empirically. You define success, run experiments, inspect failures, and use evidence to decide what to build next.
You care deeply about customers and can turn a high-level product idea into a deployed solution. You balance speed with sound engineering judgment.
You take initiative, learn quickly, and collaborate generously. You’re comfortable with ambiguity and make the people around you better.
