AI Software Engineer Jobs

View detail

As a Software Engineer on the AI Voice Agent team, you will work on real-time speech pipeline systems including live audio buffering, streaming, latency optimization, and integrating with speech providers. You will build and improve conversation intelligence systems that manage the LLM layer for natural conversation flow, including prompt construction, context management, function calling, and dialogue management. You will develop the action framework that allows the AI Voice Agent to execute tasks during calls such as querying account data, creating tickets, and checking order status, handling API configuration, success/failure branching, authentication management, and runtime execution. Additionally, you will work on knowledge ingestion, storage, and retrieval for the voice agent and manage memory for retaining information across conversations to improve responses. You will collaborate with designers to create easy-to-use interfaces for agent lifecycle management including creation, configuration, testing, and deployment. You will contribute to building evaluation frameworks and metrics for voice AI quality, post-call analytics, and instrumentation, as well as participate in the on-call rotation.

View detail

As a Software Engineer on the AI Voice Agent team, you will work on real-time systems involving live audio such as buffering, streaming, and latency optimization, along with integrating speech providers. You will build and improve conversation intelligence systems, including prompt construction, context management, function calling, and dialogue management to make conversations feel natural. You will develop the action framework to execute configurable API calls, manage success/failure branching, authentication, and runtime execution during calls. You will work on knowledge ingestion, storage, retrieval, memory, and context for the voice agent to improve its performance over time. Additionally, you will collaborate on agent lifecycle tasks such as creation, configuration, testing, and deployment of voice agents and help build evaluation frameworks for model performance, call quality metrics, and call analytics. Participation in on-call rotations is also expected.

View detail

As a Senior Software Engineer on the AI Voice Agent team, you will work on real-time systems involving live audio streaming and latency optimization integrated with speech providers. You will build and improve conversation intelligence systems that manage LLM layers, including prompt construction, context management, function calling, and dialogue management to create natural, actionable phone conversations. You will develop the action framework allowing configurable API calls with branching logic and runtime execution, supporting tasks like data lookup and ticket creation during calls. You'll manage knowledge ingestion, storage, and retrieval to enhance agent memory and learning over time. You will collaborate with designers to enable customers to create, configure, test, and deploy voice agents through intuitive product experiences. Additionally, you will help develop evaluation frameworks, analytics, call quality metrics, and monitoring instrumentation, and participate in on-call rotation duties.

View detail

As a Staff Software Engineer in the Foundations department, responsibilities include leading the design and implementation of highly scalable systems for the Managed AI offerings, driving the long-term technical roadmap for the Foundations team to support growth and evolving AI workloads, working cross-functionally with Cloud Engineering to align technical goals and solve integration challenges, leading by example through high-quality code contributions and mentoring Senior and Staff-level engineers, championing reliability, observability, and performance by identifying and resolving systemic bottlenecks, and staying current with AI infrastructure trends to ensure efficient and powerful tools are utilized.

View detail

You will be building innovative customer support AI products by defining AI-first product development through UI/UX, capabilities, and data models. Day-to-day responsibilities include taking ownership of challenging problems from idea to production, working closely with coding agents as a core part of your workflow, building tooling and feedback systems that enhance their effectiveness, and exercising engineering judgment to determine when outputs are ready to ship or need iteration. Senior engineers will own features end-to-end, while staff-level engineers will have opportunities to shape the technical direction of the team.

View detail

As a Software Engineer and member of the Platform Stability team, you will help build, fine-tune, and maintain a novel AI-powered tool for diagnosing technical issues and identifying root causes. You will collaborate cross-functionally to gather requirements, develop AI/ML and analytical models, and drive data-driven insights as part of a high-performing team. Responsibilities include designing and implementing agentic AI systems with structured interfaces, reasoning loops, and robust error handling; building and maintaining data pipelines, scheduled workflows, and benchmarking infrastructure; developing evaluation and scoring systems to measure and improve model output quality; integrating the platform with internal and external services such as ticketing, messaging, storage, and observability; collaborating with cross-functional teams to translate business requirements into technical AI solutions; and architecting and maintaining production-grade AI solutions with a focus on scalability, reliability, and performance.

View detail

As a Software Engineer, Agents, you will build systems that make AI agents indispensable to legal professionals by designing environments and actions for agentic professional work, making model selection decisions, managing context windows, creating optimal tools, and developing evaluation harnesses for faster iteration loops to unlock new capabilities. You will partner with customers and product managers to understand legal workflows, design practical evaluations to capture what excellence means, and ship agents that effectively complete tasks. Additionally, you will optimize agent performance through prompt engineering, model selection, tool design, skill writing, context window management, and evaluation harness development. You will work with the model infrastructure team to design and implement infrastructure for low-latency agent execution, including caching strategies, parallel tool calls, or subagent patterns. Improving observability and instrumentation to profile agent behavior, identify bottlenecks, and drive optimization decisions is also part of the role. Staying current on new developments in agentic systems and applying those insights to product development is expected.

View detail

Lead and scale Horizon3.ai's Offensive Engineering organization, overseeing teams responsible for exploit development, offensive content, and attack automation within the NodeZero platform. Set clear technical and product direction for how NodeZero identifies, exploits, and validates vulnerabilities across large, complex environments. Partner with Product, Precision Defense, and Platform teams to define and deliver offensive capabilities that influence the roadmap and enhance customer outcomes. Drive execution from proof-of-concept through production to transform cutting-edge attack research into scalable, productized features. Stay hands-on to guide architectural decisions and evaluate exploit and automation approaches, mentoring technical leads in building resilient, modular systems. Build, mentor, and scale diverse teams of software engineers, exploit developers, and offensive researchers, fostering a culture of collaboration, creativity, and engineering excellence that bridges offensive and product software development. Collaborate across engineering, product, and GTM teams to align offensive innovation with business priorities and ensure delivery of impactful capabilities for customers. This role is central to the mission of delivering continuous, autonomous security testing at scale.

View detail

The Full Stack Engineer is responsible for building and maintaining backend services in Python, contributing to APIs and microservices with clean and maintainable abstractions, working with datasets and asynchronous processing pipelines, improving performance, reliability, and observability, participating in system design discussions and learning from senior engineers, collaborating closely with frontend and AI/ML engineers, writing production-quality, testable, and secure code, and participating in code reviews to continuously improve.

View detail

The Product Engineer — Search at Firecrawl is responsible for owning the developer-facing search experience by shipping retrieval and ranking improvements from research as a usable product. The role involves shipping the entire product change including API updates, documentation, and examples. The engineer owns the search API end-to-end, ensuring the integration, usage, and build experience is smooth, covering response format, latency, error handling, pagination, and filtering. They use the API themselves to identify friction points before users do, closely monitor user feedback from GitHub, Discord, and support tickets, and translate research insights into product decisions in collaboration with the Search/IR and RL Research Engineers. Additionally, they run fast product experiments by hypothesizing, instrumenting, shipping, measuring, and iterating quickly to improve the search product. They are also expected to raise the bar on developer experience by fixing inconsistencies in response formats, error messages, and documentation proactively.