We’re an early-stage, US-based AI startup building a 0→1 AI-native software platform.

We’re currently operating in stealth and are looking for an exceptional senior engineer to join our small team in Pune. You’ll work directly with the founders and have meaningful influence over the product, architecture, and engineering practices from an early stage.

This is a hands-on role for someone who wants to build, own, and shape a product.

What you’ll own

You’ll take meaningful parts of the product from idea to production: shaping technical approaches, making architecture decisions, writing production code, testing, deploying, observing, and continuously improving what you ship.

You’ll work across Python, TypeScript, React/Next.js, Node.js, and PostgreSQL, building both the core application and the AI-powered workflows behind it.

You’ll help us build production-grade AI systems. That includes LLM orchestration, structured outputs, retrieval-augmented generation (RAG), tool/function calling, multi-step AI workflows, evaluations, guardrails, security and privacy controls, observability, failure handling, and cost/performance optimization.

You’ll make thoughtful decisions about model selection, prompt and context design, token usage, latency, quality, and cost, and understand when techniques such as retrieval, model routing, caching, fine-tuning, or workflow orchestration are appropriate for a production system.

You’ll design and operate AI workflows involving sequential and parallel stages, dependencies, retries, validation, and failure recovery, while recognizing when a simpler deterministic solution is the better engineering choice.

You’ll work directly with the founders to turn product ideas and customer learning into software, while helping establish the technical standards and engineering practices of a growing team.

What we’re looking for

- 8+ years of professional software engineering experience, with substantial experience owning and shipping production applications end-to-end.




- You have personally shipped AI/LLM-powered products or features to production that were used by real users.
- Strong Python expertise is required. You should be comfortable designing and building production systems in Python.
- Strong hands-on experience with TypeScript/JavaScript, React or Next.js, Node.js, and PostgreSQL or comparable relational databases.
- Practical experience building production AI/LLM systems using capabilities such as RAG, structured outputs, tool/function calling, multi-step workflow orchestration, evaluations, guardrails, and observability.
- Experience making production decisions around model choice, prompt and context design, token usage, latency, quality, and cost.
- Understanding of retrieval, model routing, caching, fine-tuning, and orchestration patterns, including the judgment to determine when each is and is not appropriate.
- Strong fundamentals in application security, authentication/authorization, API design, data modeling, testing, observability, privacy, and production reliability.
- Strong architecture and engineering judgment. You can take ambiguous product problems, reason through technical trade-offs, and independently turn them into well-engineered software.
- A strong product mindset. You care about what users need and why we’re building something, not just how to implement it.
- Deep technical curiosity. You actively keep up with advances in AI, developer tooling, frameworks, infrastructure, and software engineering and have the judgment to distinguish genuinely useful advances from hype.

You might be a great fit if

You’re the kind of engineer who experiments with a new model, framework, architecture, or development tool because you want to understand what it makes possible.





You enjoy moving between product thinking, architecture, and implementation. You’re comfortable making decisions when the answer isn’t obvious, and equally comfortable changing direction when the evidence says you should.

You value speed, but not at the expense of building something brittle. You know when to keep things simple, when to invest in stronger foundations, and how to make those trade-offs explicit.

When building with AI, you naturally ask: How do we know this works? How does it fail? How do we evaluate it? How do we keep user data safe? What should happen when the model gets it wrong?

And above all, you still want to be a hands-on builder.

Why join now

You’ll join early enough to have real influence over the product and technical foundation of the company while working directly with the founders.

As the engineering team grows, this role has the chance to expand into technical leadership for someone who demonstrates the engineering judgment, ownership, and leadership ability to take on that responsibility.

Location: Pune, India

Employment: Full-time

Compensation: ₹45–55 LPA, depending on experience and fit.

We’re intentionally keeping the company in stealth while we build. We’ll share significantly more about the product, founders, and company during the interview process.

Application question

Along with your application, please briefly describe one AI/LLM-powered product or feature you personally helped ship to production and that was used by real users.

In approximately 200-400 words, tell us:

- What did the product or feature do?
- What did you personally own or build?
- What was the most challenging technical or product problem you encountered, and how did you approach it?
- How did you evaluate whether the AI behavior was working as intended?

Please focus on your own contribution and decisions, rather than describing the work of the broader team. Please do not share any confidential information, proprietary code, customer names, or other sensitive details.

📌 Senior Full Stack Engineer (Pune)
🏢 Cenmor
📍 Pune