Company Description
Sia is a next-generation, global management consulting group. Founded in 1999, we were born digital. Today, our strategy and management capabilities are augmented by data science, enhanced by creativity, and driven by responsibility. We are optimists for change, and we help clients initiate, navigate, and benefit from transformation.
With expertise across a broad range of sectors and services, our consultants serve clients worldwide from offices in many countries. Our AI and Data teams combine data science, generative AI, and engineering to take solutions from proof of concept to large-scale deployment.
Our Mumbai office launched in 2024. We are building the team with people who want to shape something from the ground up, combining the agility of a start-up with the backing and reach of a global brand. The AI Factory in Mumbai builds and delivers production-grade Generative AI and Agentic AI solutions for enterprise clients across North America, Europe and the Middle East.
Job Description
Sia is building AI-powered products and a GenAI practice, and we are a privileged partner of OpenAI and Anthropic. We need a hands-on architect who will own the end-to-end architecture of our AI products, from system design to production scale.
You will be the hands-on leader and technical authority for our internal teams and the person client tech teams hold accountable for the architecture.
What you will do
Own the end-to-end architecture of our AI products: system design, service boundaries, data flow, APIs and non-functional requirements
Design microservice-based systems that scale, deploy on Kubernetes, and run reliably in production
Architect LLM solutions: RAG pipelines, agents, tool use (including MCP), memory and context management, and prompt management
Define evaluation approaches for prompts, models and agents, including regression testing
Build observability and traceability for AI: tracing of prompts, tool calls and agent steps, plus monitoring of latency, quality and cost
Control AI cost and performance through model selection, token budgets, caching and routing
Design for security and compliance: data privacy, PII handling, access control, prompt-injection defences and Responsible AI
Write production code, build reference implementations and review critical code
Set the team's agentic coding practices: AI-assisted workflows, review standards and quality gates
Be accountable to client tech teams for architecture reviews and answers on scalability and security
Mentor engineers and raise the technical bar across internal teams
Qualifications
Must have
10+ years in software engineering, with recent years as an architect of production systems
Strong Python and the ability to work across the stack
End-to-end design of distributed, microservice-based systems at scale
Hands-on cloud experience (AWS, GCP or Azure), including managed LLM platforms such as Bedrock, Azure OpenAI or Vertex AI
Hands-on Docker and Kubernetes
LLM application experience (OpenAI and Anthropic APIs): RAG, vector databases and agents
Experience with observability, traceability LLM evaluation and guardrails for AI systems
Secure design for AI systems (privacy, PII, compliance)
Daily use of agentic coding tools (such as Claude Code) and experience setting team practices around them
Clear communication with the CTO, client engineers and business stakeholders
Good to have
Event-driven architecture and domain-driven design
Model and vendor strategy: build vs buy, multi-model routing, avoiding lock-in
Reliability engineering for AI systems: SLOs, failover, rate limits and fallback when a provider is down
Architecture governance: decision records, reviews and reference architectures
Translating business needs into non-functional requirements
Additional Information
What We Offer
The opportunity to work on production AI for global enterprise clients, as part of a growing AI engineering capability.
The chance to learn through real client implementations and to build reusable agent assets for the AI Factory.
Access to Sia's leadership and training programmes as you grow.
A collaborative, multidisciplinary team working across varied projects and industries.
Position based in Mumbai (onsite)
Equal Opportunity
Sia is an equal opportunity employer. Decisions on hiring, promotion, remuneration and discipline are made solely on performance, competence, conduct and business needs.
Sia is an equal opportunity employer. All aspects of employment, including hiring, promotion, remuneration, or discipline, are based solely on performance, competence, conduct, or business needs.
Summary
Hands-on architect owning end-to-end architecture of AI products, from system design to production scale, designing microservice-based systems on Kubernetes and LLM solutions including RAG pipelines, agents and prompt management. Requires 10+ years in software engineering, strong Python, cloud experience (AWS, GCP or Azure) and LLM application experience with OpenAI and Anthropic APIs.
Responsibilities
Own end-to-end architecture of AI products; design microservice-based systems on Kubernetes; architect LLM solutions (RAG, agents, MCP, memory, prompt management); define evaluation approaches; build observability and traceability; control AI cost and performance; design for security and compliance; write production code; set agentic coding practices; mentor engineers.
Qualifications
10+ years in software engineering with recent years as an architect of production systems; strong Python; end-to-end design of distributed, microservice-based systems at scale; hands-on cloud (AWS, GCP or Azure) including managed LLM platforms; Docker and Kubernetes; LLM application experience (OpenAI and Anthropic APIs); observability, LLM evaluation and guardrails; secure AI design; daily use of agentic coding tools; clear communication.
Experience requirements
10+ years in software engineering, with recent years as an architect of production systems
Benefits
Access to Sia's leadership and training programmes; opportunity to work on production AI for global enterprise clients; collaborative, multidisciplinary team.
