Location: India Remote / Hybrid
Experience 6–10 years of total experience in backend or distributed systems engineering, with at least 3–4 years of hands\-on, production\-focused experience in Generative AI or LLM\-based systems.
Role Overview
We are building the next generation of AI\-native products, and we're looking for an AI Solution Architect to be a core part of that foundation.
This is not a consulting or advisory role. You will own architecture end\-to\-end — designing agentic systems, LLM\-powered platforms, and the orchestration layers that make them production\-ready at scale. You'll work at the intersection of cutting\-edge AI research and real\-world engineering constraints, shaping how we build and evolve our AI platform.
If you're excited by the complexity of multi\-agent systems, the challenge of making LLMs reliable and cost\-efficient in production, and the opportunity to set architectural standards in a fast\-moving AI\-native environment — this role is for you.
Key Responsibilities
System Architecture
- Design and own scalable architectures for agentic AI systems and LLM\-powered platforms
- Architect multi\-agent systems including planner\-executor patterns, tool\-using agents, workflow automation agents, and dynamic routing and orchestration
- Define system design for RAG pipelines, memory systems (short\-term, long\-term, vector\-based), context management, prompt orchestration, and stateful workflows
Pipeline Engineering
- Build and optimize AI pipelines for latency, cost (token optimization), scalability, and reliability
- Design integration patterns with enterprise systems — APIs, databases, and downstream services
Reliability \& Governance
- Establish observability, tracing, and evaluation frameworks for AI systems
- Define guardrails, safety layers, and failure handling mechanisms
- Drive best practices in prompt engineering, system design, and AI architecture
Collaboration
- Work closely with engineering, product, and research teams to translate use cases into production\-grade systems
- Contribute to platform\-level thinking — tooling, SDKs, reusable components
Required Skills \& Experience
Technical Experience
- 6–10 years in backend engineering or distributed systems
- 3–4 years of hands\-on, production\-grade experience with Generative AI or LLM\-based systems
- Demonstrable experience shipping AI systems at scale — not just prototypes
Generative AI \& LLM Skills
- Strong understanding of LLM architectures, capabilities, and limitations
- Hands\-on experience with agentic orchestration frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or comparable tools
- Experience with RAG architectures, embedding models, and vector databases
- Strong prompt engineering and context design skills
Architecture \& Systems
- Expertise in system design, scalability, performance optimization, fault tolerance, and cost optimization
- Experience designing backend systems and APIs
- Understanding of async workflows and event\-driven architectures
- Familiarity with cloud platforms (AWS, Azure, or GCP)
- Exposure to MLOps / LLMOps workflows
- Familiarity with observability and tracing tools
Soft Skills
- Ability to translate ambiguous business problems into concrete, scalable AI architectures
- Comfort operating as a senior IC in a fast\-moving, AI\-native environment
Preferred Qualifications
- Experience building AI platforms, internal tooling, or developer\-facing SDKs
- Understanding of AI governance, security, and compliance
- Exposure to open\-source LLM ecosystems (Llama, Mistral, etc.) in addition to proprietary APIs
MBA