If you are excited about building at the frontier of AI, consumer social, and interactive entertainment, we would love to hear from you. At Sekai, you will work with an AI-native team, move fast, own meaningful problems, and have the flexibility to explore new ideas from an early stage.
AI Agent Engineer
Location
United States
Posted
25 days ago
Salary
0
Seniority
Mid Level
Job Description
AI Agent Engineer
Sekai
Role Description Sekai is building the TikTok for mini apps — an AI-driven consumer platform where people create, remix, share, and play interactive content instantly. We are a Series A company backed by Khosla, a16z, Mayfield, and A*, with $30M raised to date. We are remote-first across all positions and are looking for ambitious, AI-native builders who want to help shape the next generation of consumer social products. We’re doubling down on creation quality and reliability. This is a key role with real ownership: the person will run the lane end-to-end and set the technical bar for agent-driven app generation. You will own: - Designing and owning the agent runtime and orchestration layer - Building long-horizon agent workflows: - prompt → plan → generate → run/validate → repair → publish - Developing robust evaluation and quality loops including eval harnesses, regression testing, and failure taxonomy - Designing model strategies including routing, benchmarking, reliability improvements, and cost/latency optimization - Creating debuggable agent systems with tracing, metrics, alerts, and observability Qualifications - Have experience building agentic systems involving tool use, orchestration, retry/repair loops, and context management - Are comfortable working with modern agent frameworks, such as LangChain, LangGraph, Google ADK, Pi-mono, or Vercel AI SDK - Are strong engineers in Python or TypeScript - Have experience shipping and operating production systems - Have strong product instincts and can translate user experience goals into system design decisions Requirements - Bonus points for having built a coding agent, devtool, IDE assistant, or code generation pipeline - Experience building evaluation frameworks (automated scoring, regression suites, release gating) - Experience designing MCP-style tool protocols or robust tool interfaces for LLM systems Benefits - Competitive compensation: salary + equity - Health coverage: we cover full medical insurance / health insurance Company Description If you are excited about building at the frontier of AI, consumer social, and interactive entertainment, we would love to hear from you. At Sekai, you will work with an AI-native team, move fast, own meaningful problems, and have the flexibility to explore new ideas from an early stage.
Related Guides
Related Categories
Related Job Pages
More Engineer Jobs
• Conduct finite element analyses (FEA) of challenging dynamic structural applications that include contact, nonlinear material behavior, transient heat transfer and fracture using the explicit finite element code LS-DYNA. • Lead design and analysis of vehicle structures • Lead test planning and data analysis with potential for onsite test support. • Develop digital twins of complex structural tests including test response, data analysis and comparison with simulations. • Perform engineering analyses on a variety of structures projects. • Lead proposals for new research and development opportunities with government and industry clients. • Conduct face-to-face meetings and prepare technical and cost proposals.
• Conduct finite element analyses (FEA) of challenging dynamic structural applications that include contact, nonlinear material behavior, transient heat transfer and fracture using the explicit finite element code LS-DYNA. • Construct finite element meshes of complicated geometries. • Assist in test planning and test data analysis with potential for onsite test support. • Develop digital twins of complex structural tests including test response, data analysis and comparison with simulations. • Perform engineering analyses on a variety of structures projects. • Identify and qualify new research and development opportunities with government and industry clients. • Conduct face-to-face meetings and prepare technical and cost proposals.
ASIC Verification Engineer
TensordyneTensordyne is a system solution company that specializes in the design of industry-leading high-performance, low-power AI inferencing. Our mission is to enable multimodal Generative AI inference acceleration at scale by providing safe, sustainable, high-performance AI-driven solutions for many markets. We are at the leading edge of advancing the latest research and product improvements for AI inference solutions that will make AI even more advantageous for compelling new applications. Well-funded, fast-paced startup company with headquarters in Sunnyvale, CA, and Munich, Germany. Many talented team members working remotely. Prioritize employees' well-being and their families. Value contributions and offer tailored benefits.
Role Description As a member of Recogni’s ASIC team, you will be responsible for the pre-silicon correctness and quality of a high-performance and low-power convolutional neural network accelerator ASIC that forms the core of the company’s flagship perception module product for autonomous driving applications. This ASIC’s design closely couples novel computational accelerator units with 3rd-party SoC IP blocks to form an end-to-end vision perception module that achieves record-breaking computational performance at low power. - Ensure the pre-silicon correctness and quality of a multi-million gate ASIC that integrates computational accelerators and 3rd-party SoC IP blocks. - SoC/Subsystem verification of embedded CPUs such as ARM/RISC-V and interconnect subsystem (including C and assembly diag validation). - Develop the block-level, sub-system and full-chip verification environment and tests to implement test plans. - Work closely with design and architecture teams to understand the functional and performance goals of the design; and work together to make the design-under-test work under all specified circumstances. - Triage and debug functional and performance issues with the design-under-test. - Handle bug tracking and coverage convergence. - Perform diagnostic and post-silicon validation tests in the lab. Qualifications - 2+ years of ASIC verification experience. - Knowledge of ARM/MIPS/RISC-V Architecture. - Familiarity with AMBA/APB/AXI Protocol. - Familiarity with processor peripheral interfaces like SPI, eMMC, *MII, GPIO, I2C. - Excellent Verilog/System Verilog programming skills. - Experience with UVM (or similar). - Deep understanding of object-oriented programming principles, constrained random stimulus, and a coverage-driven verification approach. - Scripting experience (Python, Perl, TCL, shell programming) highly-desirable. - Interest to explore AI architectures for convolution, transformer and other kinds of workloads. - Self-starter and highly-motivated to work in a dynamic start-up environment. - B.S. (M.S. preferred) degree in Electrical or Computer engineering (or similar field). Benefits - Ground floor opportunity with the team; be part of shaping one of the most exciting new companies. - Learning and development opportunities from a highly diverse and talented peer group, including experts in a wide range of fields, from Artificial Intelligence & Computer Vision to Systems & Device Engineering. - Competitive benefits package including Medical, Vision, Dental. - Perks including meals, snacks, drinks and us! - Sharp, motivated co-workers in a fun office environment. - Flexible work hours & generous PTO policy.
• Take projects from spec to deployed software, with Claude Code (and other coding agents where they fit) doing most of the typing • Author CLAUDE.md files, skills, and prompt systems that produce consistent output • Manage context, sub-agents, memory, and tokens across long-running tasks • Drive TDD with agents using hooks, sub-agents, and verification patterns, and don't let the agent cheat • Set up CI/CD, deployments, databases, secrets, and monitoring properly • Be the final quality gate. Review what the agent produced, refactor what's wrong, ship what works

