What's In It For You

- Build a proprietary AI-native delivery platform from the ground up: you own the architecture, not inherit someone else's technical debt.
- Significant scope and influence in a from-zero company.
- Competitive compensation.
- An anchor client engagement already underway: your work ships into real, production work within weeks.
- Outsized leverage: your architecture and technical decisions compound directly into client outcomes and company growth.
- The chance to build for regulated, high-stakes domains such as healthcare, life sciences, financial services and more, where quality and trust are the actual product.
- A small, talented team with no legacy codebase and no bureaucracy, working alongside founders with deep services and product pedigree.
- A modern office environment in Gurgaon, with a clear path to leading a fast-growing engineering organisation as we scale.

Duties & Accountabilities
- Own the end-to-end architecture of our AI-native delivery platform, from how work is planned and executed to how quality, oversight, and audit are built into every step, and personally lead the four-week build of its first production version.
- Design and build the orchestration core, the company's central IP: durable, checkpointed workflow graphs (LangGraph or similar) with human-in-the-loop gates implemented as graph interrupts, and clean pause, resume, and recovery semantics.
- Make human oversight the architecture, not a feature: every agent action is a proposal until a human approves it, every decision is an immutable, attributed record, and the full event history lives in a hash chained, append-only audit store.
- Establish an evals-first engineering culture: golden-dataset regression harnesses for every agent, output measured against explicit acceptance bars, and prompt changes treated with the same rigour as code changes.
- Instrument token economics from the first commit: telemetry that captures tokens, cost, and latency for every step, cost-per-story visibility, and ongoing model-mix tuning to keep unit economics honest.
- Recruit, hire, and lead a small (≤5-person) senior platform engineering team hands-on, writing code daily,

not just reviewing it.
- Be personally accountable for client implementation success: work directly with delivery teams at client sites to ensure the platform works for them in practice, and make sure what you learn from real engagements shapes what gets built next.
- Build toward the compliance and security standards our clients expect (SOC 2, ISO 27001/42001, GDPR,





HIPAA-adjacent controls) as a natural consequence of the audit-first architecture, formalised as we scale,

not a day-one distraction.

- Make pragmatic build-vs-buy and technology decisions under real timeline and cost constraints, and own the resulting technical risk.
- Represent the technical roadmap directly to clients, credibly answer what we can build, and how fast, in front of a client's own technical and compliance stakeholders.
- Set strong engineering practice and discipline from day one, so the platform is never dependent on any single person.

Customer Focus

This is not a back-office architecture role. You need to be genuinely comfortable being client-facing from week one. One honest caveat: during the four-week MVP build, your client exposure is deliberately focused on the demonstration itself; the founders front the customer day to day until the platform ships.
- Demo the platform yourself and engage directly with a client's technical and compliance stakeholders: you are a credible, first-hand representative of what we can build and how fast.
- Translate real client environments (legacy systems, inconsistent documentation, regulatory constraints)

into practical architecture and delivery decisions.
- Operate comfortably at the intersection of technical depth and commercial stakes: your decisions directly influence engagement outcomes and client trust.
- Build client trust incrementally and honestly, always reporting measured results rather than aspirational claims.
- Be willing to be present, in person or closely engaged, during key client milestones and go-live moments.

Education & Experience
- Deep, demonstrable experience shipping AI/LLM-powered systems into real production use, not prototypes or side projects.
- Staff or Principal-level engineering background, with a track record of owning system architecture end to end.
- 8+ years of software engineering experience, including meaningful time in technical leadership or architect level roles. This role demands daily coding, not architecture from a distance.
- Hands-on leadership of a small (≤5-person) senior engineering team.




- Prior experience in a 0-to-1 or early-stage startup environment preferred, genuine comfort with ambiguity and building without a safety net.
- Direct client-facing or professional-services delivery experience is a strong plus.
- Experience working in or building for regulated industries, Healthcare & Life Sciences and/or Financial

Services strongly preferred.
- Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field, or equivalent demonstrable experience.

Technical Skills Required

- Workflow orchestration frameworks (LangGraph or similar), including durable, checkpointed state machines; human-in-the-loop gates implemented as graph interrupts; and resume/recovery semantics.

This is first-class required experience, not a nice-to-have. Orchestration is our core IP.
- An evals-first mindset: golden-dataset regression harnesses, measuring agent output against explicit acceptance bars, and treating prompt changes like code changes. Having no opinion on evals is a red flag for this role.
- LLM token economics: designing telemetry that captures tokens, cost, and latency per step from the first commit; cost-per-story awareness; model-mix tuning.
- Strong proficiency in Python (we build on Python 3.12), with working proficiency in TypeScript.
- Hands-on experience building AI agent or LLM-powered systems, prompt and context engineering,

retrieval-augmented generation, tool calling, and schema-validated outputs.
- Backend and API depth: FastAPI (or comparable), clean REST service design, and event-driven patterns.
- Robust data-layer skills: PostgreSQL with pgvector for embedding search, and repo indexing approaches

(tree-sitter-style code chunking plus embeddings).
- Frontend literacy in React + TypeScript, enough to guide and review a data-dense internal console.
- Cloud and infrastructure fluency, AWS first: Docker, Terraform, and GitHub Actions on AWS; broader multi cloud exposure (Azure, Google Cloud) is helpful secondary breadth.
- Practical, hands-on fluency with modern agentic coding tools (e.g., Claude Code or equivalent) is required.
- Practical understanding of modern security architecture, authentication/authorization, secrets management, encryption in transit and at rest, and designing systems for auditability against compliance frameworks (SOC 2, ISO 27001/42001, GDPR, HIPAA).
- Experience integrating with developer and IT service-management tooling. GitHub App and Jira Cloud integration experience is a strong plus.

📌 Core Tech Lead (Gurugram)
🏢 GoodSpace AI
📍 Gurugram