Back to list

Vacancy description

Agentic AI Builder in Bombay, भारत

Sia

Bombay, भारत



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



Generative AI is moving from assistants that answer questions to agents that do work. The Agentic AI Builder designs, builds and industrialises AI agents and multi-agent workflows for Sia's enterprise clients, and helps users adopt them. You will turn real business processes into agents that perform reliably in production.
This is agent engineering, not prompt writing or chatbot configuration. You will work with Forward Deployed Engineers, architects, consultants, and client teams, and you are expected to reason about orchestration, state, tools, evaluation, security, and cost, and to show with tests and measurements that an agent works.

Key Responsibilities:
  • Work with consultants and business teams to identify agent use cases and translate business processes into clear agent requirements and acceptance criteria.
  • Design agent architectures for business workflows, deciding when a single agent, a multi-agent pattern or a deterministic workflow with LLM steps is the right choice.
  • Implement orchestration, tool calling and control flow in Python using frameworks such as LangGraph, LangChain, the Claude Agent SDK or OpenAI SDK, or custom code where that is the better choice.
  • Build tools and connectors to enterprise APIs and data sources, including MCP servers, with clear schemas, error handling and permissioning.
  • Engineer context deliberately: retrieval over enterprise data, prompt and context design, and state and memory management across steps and sessions.
  • Design human-in-the-loop checkpoints for approvals, escalation and exception handling.
  • Create evaluation suites covering task success, tool-use correctness, regressions and adversarial cases, and use them to guide each release.
  • Add observability, including traces, token and cost tracking and failure analytics, and optimise for reliability, latency and cost.
  • Implement guardrails such as input and output validation, scoped credentials, prompt-injection defenses, and data-access controls.
  • Work in agile, iterative cycles: estimate effort, flag risks and dependencies early, run solution demonstrations, and document agent behaviour and limits.
  • Prepare agents for production with the FDE and architecture team, including deployment, monitoring, and operational handover.

Internal Contributions
As part of the AI Factory, you will also:

  • Package reusable tools, connectors, and agent patterns that speed up later projects.
  • Contribute to internal accelerators, demonstrations, and proposals.
  • Share knowledge on agent design, evaluation, and guardrails with the wider engineering team.

Qualifications



Education and experience

  • Bachelor's or Master's degree in Computer Science, Engineering or a related field, or equivalent practical experience.
  • 2 to 6 years of software or AI engineering experience.
  • At least one agent or LLM workflow delivered beyond proof of concept, with evidence of how it was tested and measured.
  • Professional English, written and spoken.

Technical skills (required)

  • Strong Python and software engineering fundamentals: testing, packaging, typing and asynchronous programming.
  • Hands-on experience building agents with tool calling and orchestration using at least one agent framework or SDK (LangGraph, LangChain, Claude Agent SDK, OpenAI SDK or equivalent). Experience with every named framework is not expected.
  • Understanding of agent state, memory and control flow, including retries, timeouts and failure recovery.
  • Practical experience with RAG and vector search, and with context and prompt engineering as part of a larger system.
  • Experience evaluating LLM and agent behaviour with test sets, automated checks or LLM-as-judge methods.
  • Familiarity with LLM observability and tracing, and with tracking cost and latency.
  • Experience integrating agents with enterprise APIs, databases or SaaS applications.
  • Awareness of agent-specific risks, including prompt injection, excessive tool permissions and data leakage, and how guardrails address them.
  • Cloud deployment fundamentals: containers, environment configuration and CI/CD.

Consulting and collaboration

  • Ability to explain technical decisions and limits clearly to engineers, architects, and non-technical colleagues. Comfort running solution demonstrations and gathering feedback from business users.
  • Ownership of the components you build and the ability to work with geographically distributed teams.

Good to have

  • Working knowledge of the Model Context Protocol (MCP), including building or hosting an MCP server.
  • Experience with multi-agent patterns such as planner and executor, supervisor, or handoff designs.
  • Experience with automation platforms such as n8n or Microsoft Copilot Studio alongside code-first approaches.
  • Exposure to model routing, fine-tuning, or model selection trade-offs.
  • FastAPI or other backend service experience; Kubernetes and infrastructure as code https://jobeax.com/link/iQ86AMUnpwe2GF7K in a regulated sector or collaboration with international teams and clients.

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. 

Similar vacancies

More like this role

  • Full-time
... PHI/HIPAA constraints. - Salesforce (Apex/LWC) or Java development experience. - Experience with BigQuery, PostgreSQL, or comparable data platforms. Tools & Stack - AI: Vertex AI Agent Builder, Claude API, Gemini Enterprise API. - Orchestration: CrewAI, LangChain, LangGraph. - Dev productivity: Claude Code, Cursor, GitHub Copilot. ...

Pune, भारत

... and most importantly, the patients we serve. We are EVERSANA. The AI Solutions Engineer is the hands-on builder of the AI Hub Center of Excellence. Where the AI Engineering & Enablement Lead sets architecture and governance, this role turns that direction into working, production-grade agents and AI workflows that ride ...

भारत

Company: Novo Global Business Services (GBS) Your impact begins here You will build AI-enabled applications on the SAP Business AI Platform (BAIP, formerly SAP BTP) that put Joule Skills, custom agents and external AI models to work on real business processes. As SAP BAIP Developer – AI & Agentic Applications, you will ...

Bangalore, भारत

ECI Software Solutions

Builder Developer III

  • Full-time
... the factory where agents live: tracing logging and monitoring the thoughts of the AI; deployment and rollback of prompts and models as versioned artifacts. - Domain Logic Translation (Business) turning 50 pages of accounting regulation into structured system prompts and agentic constraints. What Youll Actually Do - Set the ...

Hyderabad, भारत

  • Full-time
  • Product Management
... ideal for a builder who thrives in a fast-moving dynamic landscape. Key Responsibilities Define and own the product strategy vision and multi-year roadmap for AI-powered agentic shopping experiences in emerging markets. Translate strategy into clear requirements driving execution across global engineering and science teams. ...

Bangalore, भारत

MINDTICKLE INTERACTIVE MEDIA PRIVATE LIMITED

Mindtickle - AI Product Engineer - Machine Learning

... outputs.- Build robust integrations/webhooks to push AI-generated insights directly into workflow tools (e.g., pushing "Churn Risk" alerts into Salesforce).2. AI Logic & Agent Implementation :- Architect "Agentic" workflows where LLMs are granted permission to perform tasks.- Implement advanced RAG to ground AI outputs ...

Pune, भारत

  • Hybrid
  • Full-time
  • AI / ML
... building and shipping production LLM or agentic AI systems in pharma domain.- Must have hands-on proficiency with at least two agentic frameworks (LangGraph, LangChain, AutoGen, CrewAI), with experience debugging framework internals.- Must have direct SDK experience with Anthropic Claude API (tool use, streaming), OpenAI Assistants ...

Bangalore, भारत

  • AI / ML
... End-to-End Lifecycle Ownership : Build, deploy, maintain, and improve autonomous AI agents, custom API tools, and RAG pipelines.- Technical Implementation : Manage agentic frameworks, data integration (vector databases/knowledge graphs), and API tooling for enterprise systems.- AI Reasoning & Guardrails : Define evaluation frameworks ...

Ahmedabad, भारत

  • Product Management
Role Overview :We're looking for a Principal AI Product Manager who's equal parts strategist, builder, and visionary- someone who wants to shape the future of AI in customer experience. In this role, you'll lead the development of our Voice AI platform and its go-to-market strategy. This is a high-ownership role and an ...

Noida, भारत

  • Hybrid
... TypeScript, React, foundation models, and reusable platform capabilities. · Apply AI-assisted development tools and coding agents while ensuring quality, security, and maintainable engineering. · Develop retrieval-augmented generation, document intelligence, agentic workflows, and automation for life sciences use cases. · Integrate ...

Hyderabad, भारत