Applied AI-Agent Engineer

Jobs in JS; Seattle (WA); On-site; USD 204,000 - 216,000; Full time

Benefits offered by this job

Equity

Health benefits

Job summary

Sapience AI is seeking an Applied AI and Agent Engineer to turn models into reliable, safe product behavior. You will design agents, grounding, and tool use, and ensure dependable actions in production, coordinating with the KO graph and COGENT architecture.

The role emphasizes grounding, safety guardrails, and measurable agent quality as you evolve from prototype to production in a knowledge-driven platform used by professional communities.

Qualifications

• Five or more years in software engineering with applied AI or ML experience.
• Hands-on experience building agentic systems, LLM apps, or retrieval-augmented systems.
• Strong grounding, tool use, and limits of models.
• Experience making AI behavior safe, reliable, and observable.
• Strong Python, plus solid software engineering fundamentals.
• Rigour about evaluation and honest handling of uncertainty.
• Care for member trust and safety.

Responsibilities

• Design and build agents to understand requests, reason, and take action.
• Own orchestration, planning, and tool use; ensure dependability.
• Design for model limits; balance capability with safety.
• Ground agent behavior in KO graph and COGENT architecture for real knowledge use.
• Build retrieval that surfaces knowledge at the right time.
• Reduce confident errors through grounding and verification.
• Integrate neural and symbolic reasoning into applied behavior with partners.

Skills

Agent design

Grounding & retrieval

Neural & symbolic reasoning

Guardrails & safety

Python programming

Evaluation & instrumentation

Software engineering fundamentals

Tools

LLM frameworks

Retrieval frameworks

Vector databases

Graph access

TypeScript

Observability tooling

Job description

About Sapience AI

Sapience AI is the collective intelligence platform for professional communities. We sit above the CRMs, AMS platforms, and knowledge bases that organizations already run, and we turn the expertise scattered across them into something every member can search, act on, and share.

The intelligence a community needs is already inside it. Most organizations just cannot reach it. Knowledge lives in silos, in legacy systems, in the heads of a few experts, and in fragmented records no one can connect. We change that.

Our work is grounded in four commitments: technology elevates people and never replaces them, the best expertise is already inside the community, everything is built on trust, and every deployment is purpose-driven for the organization it serves.

Let’s achieve more, together.

Where this role sits

This role turns AI capability into product behavior members can rely on. You build the applied AI and agentic systems that let MINERVA understand a request, reason over a community’s knowledge, and take useful action.

You work where models, retrieval, reasoning, and tools come together: designing agents, grounding them in the KO graph and the COGENT architecture, and making them dependable enough for real communities.

You sit between product and the deeper AI stack, and you are the person who makes the platform actually do the intelligent thing, well and safely.

Why this role exists

Raw model capability is not a product. Members need systems that understand what they are asking, reason over the right knowledge, and act reliably, without confident mistakes.

Building agents that are genuinely useful and trustworthy is hard: grounding, tool use, orchestration, and honest handling of uncertainty all have to work together.

The Applied AI and Agent Engineer builds that. You turn models and reasoning into applied systems members trust, and you keep them dependable as the platform grows.

What you will own (Areas of Responsibility)

You hold seven areas of responsibility across applied AI. Each one is yours to set direction on, build, and measure.

1. Agentic systems

• Design and build the agents that let MINERVA understand requests, reason, and take action.
• Own orchestration, planning, and tool use, and keep it dependable.
• Design for the limits of models, not just their strengths.

2. Grounding and retrieval

• Ground agent behavior in the KO graph and the COGENT architecture so answers rest on real community knowledge.
• Build retrieval that surfaces the right knowledge at the right time.
• Reduce confident errors through grounding and verification.

3. Reasoning integration

• Integrate neural and symbolic reasoning into applied behavior in partnership with neuro-symbolic AI.
• Decide where a model should reason and where structure should carry the load.
• Turn reasoning advances into product behavior.

4. Tooling, actions, and integrations

• Build the tools and actions agents use, including safe access to systems and data.
• Make actions reliable, observable, and reversible where they should be.
• Connect applied AI to the systems a community already runs.

5. Trust, safety, and guardrails

• Build the guardrails that keep agent behavior safe and within bounds.
• Handle uncertainty honestly, and make provenance visible.
• Treat member trust as a design constraint.

6. Evaluation and iteration

• Build evaluation for agent quality, including accuracy, groundedness, and safety.
• Instrument applied systems so you can tell whether they are working in production.
• Iterate on real behavior, not just offline tests.

7. Productionization and reliability

• Take applied AI from prototype to dependable production, in partnership with ML infrastructure.
• Balance capability against latency, cost, and reliability.
• Own the behavior members experience, not just the demo.

AI-augmented ways of working

You build with AI and you build AI. You use AI assistants to move faster through applied engineering, and you apply rigorous judgment to grounding, safety, and whether a system is genuinely dependable.

The standard is human in partnership: AI accelerates the work, you own the judgment, the interpretation, and the call. The people who create the most value here are not the ones producing the most output. They are the ones turning evidence into clear, durable decisions.

What this role is not

To keep the boundary clear:

• This is not a model research role. You apply models and reasoning; research and neuro-symbolic AI develop the underlying methods.
• This is not an infrastructure role. You partner with ML infrastructure on serving; your focus is applied behavior and agents.
• This is not a prototype-only role. You are accountable for applied systems members depend on in production.
• This is not a hype-driven role. You build agents that are genuinely useful and trustworthy, not impressive demos.

What success looks like

We measure this role on outcomes the team can see:

• Useful agents. Members get systems that understand, reason, and act reliably on their knowledge.
• Grounded answers. Behavior rests on real community knowledge, with fewer confident errors.
• Safe by design. Guardrails keep behavior within bounds, and uncertainty is handled honestly.
• Dependable in production. Applied systems hold up under real use, latency, and cost.
• Measured quality. Agent quality is evaluated and improving on real behavior.
• Reasoning realized. Advances in COGENT show up as better product behavior.

Required qualifications

• Five or more years in software engineering, with strong recent work in applied AI or ML.
• Hands-on experience building agentic systems, LLM applications, or retrieval-augmented systems in production.
• Strong understanding of grounding, tool use, and the limits of models.
• Experience making AI behavior safe, reliable, and observable.
• Strong Python, plus solid software engineering fundamentals.
• Rigor about evaluation and honest handling of uncertainty.
• Care for member trust and safety.

Preferred qualifications

• Experience with agent frameworks, orchestration, and planning.
• Familiarity with knowledge graphs and neuro-symbolic reasoning.
• Experience with retrieval, embeddings, and hybrid search.
• Experience productionizing AI features at scale.
• Domain understanding of professional or knowledge-intensive communities.

How you work

• You name the real problem before reaching for a model or an agent.
• You are honest about what works, what does not, and what it will take.
• You treat grounding, safety, and trust as design constraints.
• You build systems that are dependable, not just impressive.
• You measure real behavior and iterate on evidence.

Skills & Competencies

• Agent design, orchestration, planning, and tool use.
• Grounding, retrieval, and reducing confident errors.
• Integrating neural and symbolic reasoning into applied behavior.
• Guardrails, safety, and provenance.
• Evaluation and instrumentation of AI behavior.
• Productionizing AI features reliably.
• Software engineering fundamentals for AI systems.

Services & Tools Experience

• LLM application and agent frameworks, plus orchestration tooling.
• Retrieval frameworks, vector databases, and graph access.
• Python as the primary language, plus TypeScript where needed.
• Evaluation and experiment-tracking tooling.
• Observability for AI behavior in production.
• Cloud platforms and containers.
• Building applied behavior on the MINERVA platform, KO graph, and COGENT architecture.

Prior Experience & Background

• Prior applied AI, ML engineering, or agent engineering at a software or AI company.
• A track record of shipping AI features that people actually rely on.
• Experience making AI behavior safe and dependable in production.
• Experience with grounding and retrieval systems is a plus.

Cross-functional partners

You work most closely with Product, Neuro-Symbolic AI, Knowledge Graph Engineering, ML Infrastructure, and Research. You turn the COGENT architecture and the KO graph into dependable applied behavior inside MINERVA.

Compensation

Base Salary: $204,000 - $216,000 + early stage equity

Generous health and wellness benefits

Sapience AI is an equal opportunity employer. We do not discriminate on the basis of gender, race or color, ethnicity or national origin, age, disability, religion, sexual orientation, gender identity or expression, veteran status, or any other protected characteristic. If you need an accommodation to complete our application process, let your recruiter know.