AI Architect

KnackLabs; Hyderabad; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

KnackLabs is seeking an AI Architect to design the systems behind client engagements, including AI agents, RAG systems, automation platforms, and scalable backend architectures. This is a hands-on design role with direct client interaction and accountability for production performance.

You will own architectural decisions, defend them in reviews, and collaborate with a KnackLabs engineering team in Hyderabad, with occasional travel to client sites.

Qualifications

• 7+ years of software engineering experience with direct customer engagement.
• Full-stack development with strong backend skills.
• Experience designing scalable distributed systems with data partitioning, queues, caching, and fault tolerance.
• At least 2 years of hands-on AI experience with large language models in production.
• Proficiency in Python; working knowledge of TypeScript/JavaScript.
• Experience with RAG systems, embeddings, vector databases, retrieval, and reranking.
• Strong communication and ability to defend architecture to engineers and business leaders.

Responsibilities

• Design AI agents, RAG systems, and scalable backend architectures for multiple client engagements.
• Turn business problems into system designs with clear trade-offs and rationales.
• Ensure scale and reliability through data stores, queues, caching, and horizontal scaling.
• Lead design reviews and raise the engineering bar across engagements.
• Define evaluation metrics for accuracy, safety, latency, and cost of AI systems.
• Mentor engineers and provide guidance through reviews and pairing.
• Feedback learnings into platform and internal tools.

Skills

Architectural design

Client engagement

Python

Cloud platforms

System scalability

AI production

Communication

Education

Bachelor's degree in Computer Science

Tools

Claude Code

Codex

LangSmith

Braintrust

AWS

Azure

GCP

Job description

You will work as an AI Architect who designs the systems behind our client engagements: AI agents, RAG systems, automation platforms, and the conventional backend systems around them. This is a hands-on design role, not a slide-ware role. You will scope architectures with clients, make the hard technical decisions, defend them in review, and stay accountable for how the systems perform in production.

You will work directly with clients. Everyone at KnackLabs does. You will sit in design discussions with client engineering teams, present architecture decisions to technical and business stakeholders, and answer for the choices you make. A full KnackLabs engineering team in Hyderabad builds with you. You own the technical design and the quality of what ships. Based at the KnackLabs headquarters, with occasional travel to client locations for workshops and reviews. This role does not involve extended on-site deployments.

Responsibilities:

• Architecture. Design AI agents, RAG systems, integrations, and the scalable backend systems around them for multiple client engagements.
• Technical scoping. Work directly with clients to turn a business problem into a system design, with clear trade-offs and clear reasons.
• Scale and reliability. Make sure what we build handles real load: data stores, queues, caching, horizontal scaling, and fault tolerance.
• Design reviews. Review designs and builds across engagements. Set the technical bar and hold it.
• Evaluation strategy. Define how we measure accuracy, safety, latency, and cost for the AI systems we ship.
• Guiding engineers. Raise the level of the engineers building with you through reviews and direct pairing.
• Feedback to the platform. Feed what you learn across engagements back into our platform and internal tools.

Requirements:

• Around 7 or more years of software engineering experience, including direct work with customers on design or delivery.
• Full-stack development experience with strength in backend technologies.
• Experience designing and building scalable applications. You understand how large-scale distributed systems work: data partitioning, queues, caching, horizontal scaling, and fault tolerance.
• At least 2 years of strong, hands-on AI experience with large language models in production.
• You build with AI coding tools like Claude Code or Codex as your default way of working. You understand Claude Skills, have written skills yourself, use them actively, and have contributed to them.
• Hands-on experience building retrieval-augmented generation (RAG) systems: chunking, embeddings, vector databases, retrieval, and reranking.
• Hands-on experience building AI agents.
• Strong programming skills in Python. Working knowledge of TypeScript or JavaScript. Experience with at least one cloud platform (AWS, Azure, or GCP).
• Clear communication. You can explain an architecture decision to an engineer and to a business leader and defend it under questioning.
• High ownership and comfort with ambiguity. You can take an unclear problem and turn it into a design.

Nice to have:

• Experience building evaluations to measure accuracy, safety, latency, and cost.
• Experience with observability and tracing tools such as LangSmith or Braintrust.
• Experience with on-premises or private cloud (VPC) deployments.
• Experience deploying AI systems in regulated industries such as insurance, banking, or the public sector.
• Experience with data engineering and pipelines.
• A history of side projects, open-source contributions, or products you shipped end-to-end.
• Experience working at a consulting or professional services firm in a client-facing delivery role.
• Stack and tools: Python, TypeScript, Claude, frontier and open-source models, RAG, agents, prompt engineering, skills, evaluations, vector databases, retrieval pipelines, AWS, Azure, GCP, public/private cloud, REST APIs, and enterprise system connectors.