AI engineer/LLM engineer

This role may require in-person interview/s.

About Osano:

Osano is an innovative B-Corporation built around a simple belief: privacy is a fundamental right. Since day one, we’ve been focused on giving modern enterprises the ability to innovate quickly, stay competitive, and earn customer trust by respecting data privacy and complying with consent guidelines. Our products help organizations operate confidently in a rapidly evolving regulatory and technological landscape.

About the Role:

We’re hiring a Senior AI Engineer to build and improve Osano AI, our intelligent privacy assistant. As part of the Osano AI team, you will take capabilities from first idea to production, with an emphasis on delivering capabilities that are reliable, measurable, and trustworthy.

This role goes beyond wrapping APIs or building chat interfaces. We are looking for an engineer who has shipped LLM-powered systems that real users depend on. That means that you’ve dealt with hallucinations, latency, cost, evaluation, and tricky edge cases within agentic systems, and you know what it takes to keep these non-deterministic systems working after launch.

You will often work on problems that aren’t well-defined. Success here depends on how you think, communicate, and work with others as much as on what you build. This position is ideal for someone who is highly technical, thrives in ambiguity, takes ownership of 0→1  initiatives, wants to have an outsized impact, and believes responsible AI is non-negotiable.

 

Responsibilities:

Build and ship production AI

• Design, build, and maintain agentic features across our products, from early prototype to scaled production deployments.
• Build retrieval (RAG) systems that build trust through verifiable sources.
• Build agentic and multi-step workflows with guardrails, observability, and structured outputs.
• Balance quality, latency, reliability, and cost in production.

Measure and improve AI systems

• Build thorough evaluation frameworks that cover accuracy, grounding, latency, and reliability, utilizing both offline evaluations and real-world production signals.
• Deploy data-driven methods to decide what to ship, how to fix it, and what to stop doing.
• Continuously refine deployed systems based on measurable outcomes.

Collaborate and communicate

• Work closely with product managers, engineers, privacy experts, and other stakeholders to decide what to build, how to build it, and why.
• Write clear design documents and run effective technical discussions.

Privacy-First Development

• Embed privacy-by-design principles across the AI stack.
• Ensure compliance, data sovereignty, and secure handling practices.
• Collaborate cross-functionally to align AI capabilities with regulatory standards.

About You:

• You’re curious, self-directed, and motivated to learn quickly.
• You’re comfortable navigating ambiguity and creating clarity for others.
• You’re excited about privacy, responsible AI, and building trustworthy technology.
• You are willing to relentlessly pursue the best, most responsible ways to leverage AI—without overselling its capabilities or ignoring its limitations.

 

Must-Haves:

• 5+ years of professional software engineering or AI/ML experience
• Demonstrated experience building and running agentic systems in production with real users, not just prototypes or internal demos.
• Deep technical understanding of LLM usage and orchestration beyond prompt engineering.
• Proven experience building complex RAG systems and autonomous AI agents.
• Clear written and verbal communication. You can explain technical trade-offs to both engineers and non-technical stakeholders.
• Concrete examples of getting from ambiguity to results.

Nice-to-Haves:

• Strong expertise in the Python AI ecosystem, including FastAPI and LangGraph.
• Experience with Knowledge Graphs to enhance RAG precision
• Familiarity with Privacy-Enhancing Technologies (PETs)
• Experience with data anonymization techniques
• Background in compliance-heavy or regulated environments

 

Why Us:

• We're a welcoming team that's dependable, curious, moves fast, and full of talented people
• We're a B-corporation with a mission that matters, in a high-growth space with significant potential
• You'll have access to our training program, well-defined career paths, and a leadership team that values professional development

Benefits:

• Competitive-pay compensation and ownership interest/equity
• Unlimited paid time off, plus a requirement to take at least two weeks off per year
• We're a Best Place for Working Parents and offer paid parental leave for all new parents
• Osano sponsors individual premiums on base plans at 100% and dependent premiums at 50% for Medical, Dental, and Vision insurance via Aetna
• A fully and permanently remote company, so you can work from anywhere in the U.S.
• Receive a MacBook and $600 to craft your home workspace
• Annual company trip designed to foster connection, creativity, and fun
• Mental health benefits with free memberships to mindfulness and talk therapy services

Location

Fully remote, office-based, or hybrid work options are available.

About the company

A global technology provider builds software platforms and data-driven solutions for performance monitoring, analytics, and operational optimization across international markets.

The project integrates agentic AI into a sports performance platform, turning athlete data into reliable, scalable insights for coaches and performance specialists.

Responsibilities

• Design and ship specialist AI agents that use memory, tools, data, and multi-step reasoning, including multi-agent orchestration that routes work, manages dependencies, and synthesizes conflicting outputs.
• Build confidence, uncertainty, and consequence assessment mechanisms plus human-in-the-loop escalation so the system decides when to answer, request more information, or defer to a human.
• Turn sport scientist expertise into validated, versioned, testable agent capabilities, supported by evaluation, observability, and regression testing to measure and improve production performance.
• Work with domain experts to ensure AI outputs are grounded, traceable, and actionable, with calibrated confidence levels and transparent evidence, and avoid unsupported recommendations when evidence is insufficient.

Requirements

• 5+ years of professional experience in applied ML, AI, or software engineering, with strong Python and software engineering fundamentals for building, deploying, and operating production systems.
• Hands-on experience personally building production agentic AI systems used by real users, including persistent memory/state, tool calling, multi-step reasoning, workflow orchestration, and production operations; chatbots, prompt engineering, or RAG alone are insufficient.
• Hands-on experience building or significantly contributing to production multi-agent systems, including agent routing, orchestration, specialist agent composition, dependency-aware workflows, parallel and sequential execution, conflict resolution, and response synthesis.
• Practical experience with probabilistic model calibration, including Platt scaling, isotonic regression, Expected Calibration Error (ECE), reliability/calibration curves, and confidence and uncertainty estimation; English at Upper-Intermediate or above.