Source Job

Austria

  • Build and maintain AI agent harnesses: tool calling, agent loops, context management, structured outputs.
  • Develop reusable tools and modules for AI across model types and sizes.
  • Design resilient systems for network failures, model errors, timeouts, and retries.

JavaScript TypeScript Distributed Systems

20 jobs similar to AI Harness Engineer

Jobs ranked by similarity.

$100,000–$120,000/yr
Global

  • Build and ship working software for brokerage clients, from discovery to production, using AI-assisted development.
  • Work directly with brokerage executives to identify needs, create specs, and deliver solutions in days, not weeks.
  • Own the full lifecycle of features, including debugging, support, and productizing successful solutions for broader use.

Rechat is the operating system for real estate, combining marketing, CRM, transactions, listings, and AI into one product. The company is growing quickly, with tens of thousands of users and a collaborative, inclusive culture.

Global

  • Lead technical audits and design AI-powered solutions for client systems, platforms, and integrations.
  • Build and deploy production-grade AI agents, automations, and internal tools using modern full-stack technologies.
  • Identify recurring patterns and transform successful solutions into reusable modules for faster future delivery.

They are a specialist digital transformation consultancy that helps small and medium-sized businesses adopt AI operating systems, intelligent agents, and automation solutions. The team emphasizes technical practicality, innovation, client outcomes, and responsible AI implementation.

$150,000–$180,000/yr
Canada 4w PTO

  • Build across the product stack from Rails APIs to React/TypeScript frontends, owning problems end-to-end from customer conversation to production.
  • Work directly with founders, designers, and engineering in a high-trust, autonomous environment where AI is embedded across your workflow.
  • Ship features live, validate with data, and maintain long-term ownership of what you build, with light ceremony and high accountability.

Great Question is an all-in-one AI customer research platform that helps teams recruit participants, run research, and share insights. Backed by world-class investors, the company has a small team culture built on high trust, high agency, and high emotional intelligence.

Europe

  • Build and evolve AI-powered products with end-to-end TypeScript/React and Golang development.
  • Design and maintain robust backend systems including APIs, distributed systems, and cloud infrastructure on AWS.
  • Contribute to AI-first engineering practices, working autonomously in a remote European team.

Our partner is a technology company that builds AI-powered products integrated into partner platforms. The team is autonomous and collaborative, with a focus on reliability and correctness.

Europe

  • Lead a remote team of engineers in designing and shipping production-grade agentic AI systems for enterprise clients.
  • Own solution design and system architecture across agents, tools, data, evaluations, and controls.
  • Personally implement critical components and guide client stakeholders through difficult technical decisions.

EggAI is an enterprise-focused generative AI company that helps large organizations move AI solutions from prototyping to production. Based in Munich, Germany, the company builds safe, reliable, and scalable AI systems for enterprise clients.

$86,400–$108,000/yr
Europe

  • Build and improve LLM-powered systems to navigate complex construction tendering workflows.
  • Own features end-to-end from model/agent through API to TypeScript front-end.
  • Collaborate across teams to translate business problems into shipped AI features and maintain production systems.

Cosuno is a fast-growing tech startup that revolutionizes construction through a digital platform for tenders and procurement. With a small, well-funded team, we foster a calm, collaborative, and productive engineering culture.

UK 4w PTO

  • Design, build, and operate production-grade agentic systems for developers.
  • Develop core agent infrastructure including orchestration, tool execution, and evaluation.
  • Own projects end to end from opportunity identification to launch and iteration.

Our partner is a fast-growing Series C technology company that builds AI-powered developer tools. The organization is fully remote with an autonomous culture focused on engineering ownership and collaboration.

Global

  • Evaluate AI-generated coding interactions end to end for correctness and engineering judgment.
  • Assess whether outputs reflect strong engineering taste and provide clear, opinionated feedback.
  • Help define what great looks like for AI coding tools like Codex, Claude Code, and Cursor.

G2i Inc. is a technology staffing company that connects software engineers with remote contract opportunities. The company values engineering excellence and provides flexible, ongoing projects for senior-level developers.

UK

  • Build tooling for capturing and processing data from agents and humans at significant scale.
  • Solve hard problems around compute, orchestration, scaling, security, and reliability.
  • Help develop approaches for training, benchmarking, and evaluating AI agents.

Prolific builds human data infrastructure for AI development, connecting researchers with a global pool of participants to collect high-quality, ethically sourced behavioral data. They are a mission-driven company at the forefront of AI innovation, with a remote culture and a focus on impactful work.

Unlimited PTO

  • Architect and ship AI-powered features that change how service businesses operate, creating net-new capabilities.
  • Build and maintain large-scale systems processing billions in payments and serving 120,000+ businesses with reliability.
  • Own your work end to end from technical design through production, with full accountability for performance.

Genius AI builds AI-powered products that handle admin work for local businesses, automating booking, marketing, client management, and finances. The company has saved businesses over 106 million admin hours and facilitated more than 624 million client touch points, fostering a culture of ownership and AI-first collaboration.

Canada

  • Design and implement the core AI agent runtime in Python, including orchestration loops, tool definitions and execution, memory and context management, and failure handling.
  • Build and maintain evaluation datasets, automated evaluators, LLM-as-judge pipelines, and regression tracking to ensure agent quality and performance.
  • Develop Python and Node.js microservices for agent hosting and LLM interactions, and build reliable Laravel/PHP APIs for integration.

Jobgether is a platform that uses AI-powered matching to connect candidates with job opportunities, partnering with companies to manage applications and next steps. They emphasize a fast-growing, collaborative environment with a focus on professional growth and cutting-edge technology.

Europe

  • Architect and build production AI-agent systems like AIDA and NOVA, shaping how Yuno applies LLMs and agentic AI to payment problems.
  • Design conversational and multilingual agents that hold real customer conversations across channels, optimized for reliability and low latency.
  • Define evaluation, safety, and guardrails for agentic systems in a compliance-sensitive, multi-market environment.

Yuno is the AI-native operating system of global commerce, powering financial infrastructure for enterprise merchants, banks, and wallets. It connects over 1,000 payment methods across 190+ countries, trusted by global brands like McDonald's and Rappi, with a remote-first culture.

Global

  • Develop and maintain high-performance Back-end microservices and AI-enabled services using TypeScript and Node.js.
  • Design, implement, and integrate AI and LLM-powered platform features using AWS serverless technologies.
  • Collaborate with cross-functional teams on API-first architecture and contribute to continuous improvement initiatives.

Sigma Software is a technology company specializing in building intelligent, scalable platforms. They value engineering excellence, innovation, and collaboration, working with globally recognized publishers.

Global

  • Embed across teams to identify where AI can remove operational friction and build internal tools end-to-end.
  • Drive adoption through workshops, pairing, and office hours, measuring success by active usage.
  • Partner with Security to establish guardrails, access scoping, and audit trails for AI solutions.

LocalStack is a local cloud development platform that provides secure local sandboxes simulating cloud environments for developers and AI agents. They are a Series A startup with $25M funding, globally distributed teams across 25 countries, and a culture focused on ownership, openness, and excellence.

India

  • Build and maintain the product's core UI including map interactions, chat interface, data tables, and file-upload flows.
  • Support backend development with API design and server-side persistence alongside the team's AI engineer.
  • Contribute to an AI-powered chat interface, addressing challenges around latency and streaming partial results.

Smart Working connects skilled professionals with global teams for full-time, long-term roles. The company fosters a community-focused culture that values growth and well-being.

  • Build interfaces for AI-powered products used by millions, including real-time chat, inline agent suggestions, document editors, and agent builder tools.
  • Design and implement rich, responsive user interfaces in React and TypeScript, working across the Superhuman product suite.
  • Tackle hard interaction design problems: streaming content, complex state management, and multi-surface interactions with a strong emphasis on documentation and testing.

Superhuman builds an AI productivity platform that works across every surface, including Go (proactive AI assistant), Mail, Docs, and enterprise controls. The company is remote-first and values autonomy, trust, and a highly collaborative culture, with team member resource groups like BIPOC, LGBTQIA+, women, and parents.

Global

  • Collaborate with customer teams building production agent systems, designing and implementing agents, and improving reliability and scaling.
  • Turn recurring customer challenges into open-source improvements, fixing performance issues and shipping new primitives.
  • Work at the intersection of customer-facing engineering and core platform design, compressing the feedback loop between production usage and framework development.

Mastra is the open-source TypeScript framework for building AI agents. Backed by Y Combinator and Spark Capital, the small, fully remote team has raised $35M and achieved 27k+ GitHub stars and 1M+ weekly npm downloads in under 18 months.

Europe

  • Deliver end-to-end functionality across a TypeScript/React front end and a Golang backend.
  • Build products for partner integrations, including wallet systems and game systems in a certified environment.
  • Design and build APIs (GraphQL, gRPC, REST) and shape the architecture of a young platform on AWS.

Oddin builds products that partners integrate into their own platforms, focusing on AI-first development where 80-90% of code is generated with AI. They are a young startup with a collaborative, autonomous product team and no strict processes.

$91,000–$104,000/yr
UK 26w maternity 4w paternity

  • Drive practical AI adoption by coaching teams across commercial, operational, and engineering functions.
  • Build custom Python and JavaScript integrations and automations where off-the-shelf tools fall short.
  • Curate a central AI best-practices library and provide first-line technical support and debugging.

Genio creates beautifully simple learning tools that boost knowledge, skills, and confidence. The company supports a flexible hybrid working model with a collaborative office in Leeds and remote workers across the UK.

US

  • Build and ship a project end to end: understand the problem, build a working version, and improve it based on user feedback.
  • Work with business teams to understand their workflows and translate requirements into actionable solutions.
  • Use AI-augmented development tools as your default workflow and develop judgment about their effectiveness.

M3 is a global healthcare technology company providing innovative research and technological solutions to the healthcare industry. The M3 Group operates in the US, Asia, and Europe with over 5.8 million physician members and is publicly traded on the Tokyo Stock Exchange, ranked in Forbes' Global 2000 list.