TypeScript AI Jobs

View detail

Design and implement high-throughput, isolated processing clusters for Enterprise clients ensuring strict tenant isolation and High Availability. Drive improvements across Temporal workflow clusters and production Kubernetes environments with scaling strategies supporting self-serve consumers and Enterprise contracts. Collaborate with the AI/ML team to transform experimental models into scalable, production-ready services, owning infrastructure that connects model outputs to user-facing features with minimal latency. Build and operate high-dimensional vector database infrastructure for semantic search enabling users to find exact moments in video using natural language. Architect backend systems for bulk workflow orchestration, resource isolation, and multi-tenancy to support large media houses managing massive video archives.

View detail

Lead major cross-team platform initiatives, taking foundational systems from 0 → 1 and scaling them to support millions of users. Build shared, extensible Agent primitives that Replit Agent can reuse safely and consistently. Identify the highest-leverage technical bottlenecks such as performance, reliability, correctness, abuse, and observability, then design and ship solutions for scale. Raise the bar for engineering excellence through architecture reviews, code quality, reliability standards, and mentorship. Partner across teams to improve platform adoption, ergonomics, and velocity, turning platform work into measurable outcomes. Work on core areas including Connectors framework, content/configuration primitives, data/analytics/events and experimentation primitives, Identity & Access platform, Localization/i18n platform, Notifications & communications platform, and core web platform infrastructure including performance optimization, observability, debugging workflows, caching strategy, and reliability.

View detail

As a New Grad Software Engineer at Sierra, you will build and ship production features across backend services, APIs, and user-facing components. Collaborate with senior engineers to design, implement, and iterate on systems supporting AI agents and customer workflows. Write clean, well-tested code and participate in code reviews to learn best practices and improve system quality. Help improve the reliability, performance, and scalability of existing systems through debugging, testing, and incremental improvements. Partner with product managers, designers, and other engineers to understand customer problems and translate them into technical solutions. Learn how large-scale, real-world systems are built, monitored, and evolved in production. New Grad engineers may join various teams based on business needs, interests, and strengths, including Agent Architecture, Insights & Data, and Voice & Real-Time Systems, with flexible placement that may evolve over time.

View detail

The role involves building a product that leverages AI to help teams analyze customer interviews, uncover insights, and make faster, smarter product decisions. Responsibilities include solving problems end-to-end across the LLM pipeline, infrastructure, backend, and UX; making architectural decisions for a greenfield stack; pushing the capabilities of large language models (LLMs); and communicating clearly about tradeoffs, problems, and blockers. The position requires ownership of parts of the product, ensuring high quality output, and working on advanced AI models to deliver nuanced and effective research tools such as AI agents for project setup, interview conduction, analysis of responses, database building of people profiles, real-time video interview systems with emotional understanding, distributed information mining, and models of customer preferences and synthetic personas.

View detail

The role involves creating reference implementations for potential future products or product components by integrating new hardware platforms, sensor suits, simulators, and concepts of operation with the Hivemind SDK (C++) for commercial applications, focusing on autonomy and simulation. The role requires demonstrating developed architectures as solutions to customers, gathering feedback, and iterating accordingly. It also includes exploring and evaluating future hardware and software technologies relevant to Shield AI's product roadmap beyond current projects, identifying areas of technical debt across the software stack, and analyzing and synthesizing solutions to address them. The position requires working closely with product teams and forward-sprinting within the Special Projects team to contribute strategically and tactically to the development of foundational Hivemind products, especially Hivemind Enterprise commercial applications.

View detail

Own and lead projects and product areas end-to-end, including architecture, implementation, rollout, and long-term operations. Design ergonomic, developer-friendly APIs and abstractions for infrastructure capabilities. Build and operate reliable backend services such as rate limiting, auth, quotas, metering, and migrations with clear SLOs. Drive performance and reliability improvements through profiling, tracing, load testing, and capacity planning. Mentor teammates through code reviews, design docs, and technical leadership.

View detail

Design and evolve the agent runtime that manages reasoning, tool use, memory retrieval, and response generation. Build agent capabilities such as image generation, voice synthesis, video creation, web browsing, and code execution. Optimize large language model (LLM) integration through prompt engineering, context window management, multi-provider model routing, cost optimization, and latency reduction. Implement memory systems including long-term memory, working memory, episodic recall, and semantic search to enable agents to learn from interactions. Design autonomous behaviors including proactive actions, scheduled tasks, and goal-directed actions to make agents feel self-directed. Build evaluation and quality systems such as benchmarks, A/B testing, and metrics to assess agent behavior, personality consistency, and response quality. Experiment with new architectures like multi-agent collaboration, planning, and chain-of-thought reasoning. Collaborate with product and design teams to translate AI capabilities into intuitive user experiences.

View detail

The Platform Engineer within Forward Deployed Engineering (FDE) provides hands-on leverage by embedding with customer-tagged FDE pods to support generalization and contribute directly to architecture, product shaping, refactoring, and implementation. The role involves translating repeated cross-customer signals into platform bets by creating clear hypotheses with success criteria and validation plans. It includes raising engineering standards through tooling, mentorship, high-signal code review, pairing, and building lightweight developer tools to promote good architecture, readability, and correctness across FDE. The engineer collaborates closely with cross-functional platform teams including B2B Product, customer-tagged FDEs, ops, and business partners to deliver appropriate products and platform capabilities. Additionally, the role may lead complex platform capabilities end-to-end, acting as the direct responsible individual (DRI) from requirements through implementation, making key tradeoffs explicit, and involving customer pods early to maintain grounding in real deployments.

View detail

Lead the deployment, performance, and reliability of AI agents operating in live, high-stakes healthcare environments. Architect and scale full-stack systems integrating with EHRs, legacy healthcare platforms, and real-time voice infrastructure. Drive technical strategy for customer-facing solutions, collaborating with product and engineering to translate client needs into scalable architecture. Mentor engineers and set standards for code quality, testing, security, and HIPAA-compliant development. Shape product roadmap by identifying systemic challenges in customer workflows and proposing high-leverage technical solutions.

View detail

As a Senior Software Engineer, Backend at Centari, you will be a key player in designing and building Centari's core AI technology. You will work alongside engineers who share a bias for action, writing code, shaping the product, interacting with customers, and driving initiatives from concept to completion. You will be involved in developing systems built with Go and React/TypeScript, leveraging cutting-edge LLM technologies across infrastructure, search, and persistence layers.