Lead AI Architect - Agentic SDLC

Build the systems that change how software gets built.

We’re looking for an exceptional, hands-on Applied AI Engineer who combines deep software engineering expertise with creative thinking about developer productivity. You’re already a power user of AI coding tools, have customized your own development workflow, and are building toward a future where agents take on meaningful engineering work across the software development lifecycle.

In this role, you’ll design and build agentic workflows that connect requirements, architecture, implementation, testing, code review, deployment, and maintenance. You’ll turn promising prototypes into reliable systems that engineering teams trust and use.

You’ll partner directly with engineering leaders, developers, and customers to identify high-value opportunities, ship working solutions, and measure their impact. This role blends hands-on engineering, technical architecture, product judgment, and customer-facing leadership.

What you'll Do

·        Build coding agents that deliver real engineering outcomes. Develop agents that understand repositories, implement features, diagnose defects, write and run tests, address review feedback, and prepare changes for human approval.

·        Design agentic workflows across the SDLC. Connect issue trackers, repositories, developer environments, CI/CD pipelines, documentation, and observability tools into coordinated workflows with clear ownership and approval points.

·        Engineer reliable agent execution. Build context management, tool integrations, orchestration, isolated execution environments, state persistence, retries, and recovery mechanisms for complex engineering tasks.

·        Use AI coding tools as part of your daily craft. Apply tools such as Codex, Cursor, Claude Code to prototype, implement, debug, and refine the systems you build. Turn effective personal practices into repeatable team capabilities.

·        Build compelling demos and production-ready implementations. Create prototypes, reusable integrations, reference architectures, and automations that demonstrate value and support adoption.

·        Evaluate quality and productivity rigorously. Develop benchmarks and evaluation harnesses that measure task completion, code correctness, regression rates, security findings, latency, cost, and engineering effort.

·        Make autonomy safe and practical. Implement scoped permissions, secrets handling, audit trails, sandboxing, and human review controls appropriate to each workflow.

·        Lead technical discovery and enablement. Work alongside engineering teams to understand their constraints, run hands-on workshops, and guide adoption from initial experiments through production rollout.

·        Shape product direction through evidence. Translate deployment experience into actionable product requirements, model feedback, technical guides, and reusable engineering patterns.

What You Bring

·        5+ years of experience in software engineering, applied AI, developer tooling, platform engineering, or technically intensive solutions engineering, with a strong record of shipping working systems.

·        Strong programming skills in Python, TypeScript, or another widely used language, and confidence navigating unfamiliar codebases.

·        Deep practical experience with AI coding tools and concrete examples of workflows, integrations, or agents you have built and used.

·        Hands-on experience building LLM applications with tool calling, structured outputs, context retrieval, and iterative execution.

·        Strong understanding of software engineering fundamentals, including architecture, Git, automated testing, code review, CI/CD, debugging, and production operations.

·        The judgment to distinguish tasks that benefit from agents from those better served by deterministic automation—and to decide where human review is essential.

·        A disciplined approach to evaluating generated code and diagnosing failures across models, prompts, context, tools, and execution environments.

·        Clear written and verbal communication, including the ability to explain architectural tradeoffs and lead hands-on technical sessions.

·        Comfort with ambiguity, fast experimentation, and ownership from problem discovery through delivery and adoption.

What sets you apart

·        You’ve built agents that complete multi-step engineering tasks against real repositories.

·        You’ve developed agent evaluation frameworks, repository context systems, custom tools, MCP integrations, or orchestration infrastructure.

·        You’ve integrated coding agents into enterprise environments with meaningful security and operational requirements.

·        You’ve contributed developer tools, open-source projects, technical guides, or reference implementations.

·        You can demonstrate measurable improvements in engineering throughput or quality without shifting hidden work onto reviewers.

·        You bring a strong product instinct: you identify a valuable problem, build the smallest useful solution, and improve it based on evidence.

What Success looks like

Engineering teams adopt the workflows you build because they reliably help them ship better software. Agents complete clearly scoped tasks with measurable quality, failures are visible and recoverable, and successful experiments become reusable capabilities across teams.

Show us what you’ve built. A repository, live demo, technical walkthrough, or concrete example of an agentic development workflow will help us understand how you think and execute.