Associate Director - Agentic AI Implementation & Process Automation

SiriusAI

Gurugram District

On-site

INR 400,000 - 900,000

Full time

3 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

SiriusAI in Gurugram, India, seeks an Associate Director to lead agentic AI and process automation for US financial services clients. You will design the solution, stay close to the build, and drive production deployment and ongoing operation.

This hands-on role requires building and reviewing agentic systems, leading a team of AI engineers, automation developers and business analysts, and ensuring security, compliance and model risk requirements are met.

Qualifications

  • 8+ years in software engineering, automation or AI delivery.
  • Hands-on delivery of at least two agentic processes that went into production at an enterprise client.
  • Strong engineering background with Python, PR reviews and debugging agent behaviour.
  • Experience with one or more agent frameworks and their trade-offs.
  • Knowledge of MCP servers, A2A, and security/authentication considerations.
  • Experience deploying on cloud platforms with containers and CI/CD.

Responsibilities

  • Own the solution architecture for agentic automation engagements: agent design, orchestration, tool and MCP server design, integration with client systems, identity and access, deployment topology.
  • Lead delivery from discovery through build, testing, go-live and hypercare; decide agent vs rules/API/RPA allocations.
  • Design multi-agent systems and handoff strategies (A2A, MCP) with state management and retry logic.
  • Build and maintain evaluation datasets, tests, tracing, guardrails and monitoring for production readiness.
  • Implement role-based access control for agents and MCP tools in line with IAM and audit logging.
  • Deploy agentic solutions in large enterprise environments with security reviews and change management.
  • Set clear accuracy expectations with clients and report metrics openly throughout engagements.
  • Design modular, reusable agent templates and deployment patterns to speed future engagements.
  • Lead and coach the delivery team; perform design/code reviews and mentor junior engineers.
  • Serve as senior technical lead with client stakeholders and support pre-sales with designs and staffing.

Skills

Python
LLM-based agents
Solution architecture
Delivery leadership
Code reviews
Cloud platforms
Kubernetes
Security/compliance

Education

Bachelor's or Master's in CS/Engineering

Tools

LangGraph
CrewAI
AutoGen/Microsoft Agent Framework
Semantic Kernel
OpenAI Agents SDK
Google ADK
Claude Agent SDK

Job description

Sirius AI is an AI consulting and solutions firm working with financial services clients, including banks, fintechs, payments companies and wealth managers. Our teams design, build and run GenAI, agentic AI and ML solutions inside client environments, working alongside their operations, technology and risk teams.

About the Role

We are hiring an Associate Director to lead agentic AI and process automation work for our US financial services clients. The role combines solution architecture and delivery leadership. You will design the solution, stay close to the build, and be accountable for getting it into production and keeping it running there.

Most of our work is in operations-heavy processes such as onboarding, KYC/AML, lending, payments operations, claims and servicing, at large organisations with strict security, audit and model risk requirements. You will lead a team of AI engineers, automation developers and business analysts, several of whom are early in their careers.

This is a hands-on role. We expect you to have built and deployed agentic systems yourself and to be comfortable reviewing code, agent traces and architecture decisions with your team.

What You Will Do
  • Own the solution architecture for agentic automation engagements: agent design, orchestration, tool and MCP server design, integration with client systems, identity and access, and deployment topology.
  • Lead delivery from process discovery through build, testing, go-live and hypercare. Fix the process before automating it, and decide which steps need an agent, which are better handled by rules, APIs or RPA, and which should stay with a person.
  • Design multi-agent systems, including how agents delegate and hand off work (for example over A2A), how they reach tools and data (for example through MCP), and how state, memory, retries and failures are handled.
  • Build and maintain the harness around each solution: evaluation datasets, regression tests, tracing, guardrails, and cost and latency monitoring, so that changes to prompts, models or tools are tested before they reach production.
  • Implement role-based access control for agents and MCP tools. Define what each agent is allowed to call, on whose behalf and with what data scope, and align this with the client's IAM, secrets management and audit logging.
  • Deploy agentic solutions in large enterprise environments, which means working through security reviews, architecture boards, model risk validation, change management and integration with existing platforms.
  • Set accuracy expectations with clients early. Agree what acceptable performance looks like for each use case, how errors and hallucinations will be measured, and where human review will stay in place, then report against those numbers openly throughout the engagement.
  • Design solutions to be modular and reusable. Build up a shared library of agent templates, MCP servers for common FS systems, evaluation datasets and deployment patterns that shorten delivery on the next engagement.
  • Lead and coach the delivery team, run design and code reviews, and help junior engineers build practical skills in agentic development.
  • Act as the senior technical lead with client stakeholders and support pre-sales with solution design, estimates and staffing plans.
What You Need
  • 8+ years in software engineering, automation or AI delivery, including at least 2 years building and running LLM-based agentic solutions.
  • Hands-on delivery of at least two agentic process automation solutions that went into production at an enterprise client. You should be able to walk us through the architecture, what went wrong and how you measured results.
  • A strong engineering background. You should be comfortable writing Python, reviewing pull requests and debugging agent behaviour from traces and logs.
  • Working experience with one or more agent frameworks (such as LangGraph, CrewAI, AutoGen/Microsoft Agent Framework, Semantic Kernel, OpenAI Agents SDK, Google ADK or Claude Agent SDK) and a considered view on their trade-offs.
  • Practical understanding of MCP (building and securing MCP servers, tool design, authentication) and A2A (agent discovery and task delegation), and when each is the right fit.
  • Experience building evaluation and testing harnesses for LLM and agent systems, including golden datasets, LLM-as-judge with human calibration, regression testing and production monitoring.
  • Experience implementing access control for agents and tools, such as OAuth/OIDC, service identities, scoped tokens, least-privilege tool access, user delegation and audit trails.
  • Experience deploying on Azure, AWS or GCP using containers, Kubernetes, CI/CD and secrets management, within enterprise network, data residency and security constraints.
  • Solution architecture experience across integration patterns, including APIs, event-driven systems and RPA where no API exists.
  • The ability to explain agent behaviour, failure modes and residual risk to business, technology and risk audiences without overselling what the technology can do.
  • A bachelor's or master's degree in computer science, engineering or a related field.
Good to Have
  • Delivery experience in banking, payments, lending, insurance or wealth management operations.
  • Experience with RPA and BPM platforms such as UiPath, Power Automate, Pega, Camunda or ServiceNow.
  • Experience with agent observability tools such as LangSmith, Langfuse or Arize.
  • Familiarity with model risk management (for example SR 11-7) and AI regulation such as the EU AI Act.
  • Experience with intelligent document processing.
Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Agentic AI Engineer
Agentic AI Engineer

Flatworld Solutions Pvt. Ltd. • Bengaluru Urban

On-site
INR 1,500,000 - 2,500,000
Senior Agentic AI Developer / Solution Engineer
Senior Agentic AI Developer / Solution Engineer

Papigen • Chennai

On-site
INR 900,000 - 1,500,000
Agentic AI Developer
Agentic AI Developer

Vlink • Mumbai

On-site
INR 1,200,000 - 2,400,000
Artificial Intelligence Engineer
Artificial Intelligence Engineer

Randomtrees • Chennai

Hybrid
INR 1,500,000 - 1,900,000
Associate Manager
Associate Manager

C5i • Bengaluru

On-site
INR 3,500,000 - 5,500,000
Senior Agentic AI Developer
Senior Agentic AI Developer

Lester Infoservices • Bengaluru

Hybrid
INR 4,200,000 - 7,000,000
Senior AI Software Engineer / Agentic AI Developer
Senior AI Software Engineer / Agentic AI Developer

TelioQuantAI • Gurugram District

On-site
INR 3,500,000 - 5,500,000
Lead Agentic & Automation Architect
Lead Agentic & Automation Architect

Infosys • Hyderabad

On-site
INR 6,000,000 - 9,000,000
Enterprise AI Architect & Consulting Lead
Enterprise AI Architect & Consulting Lead

Movate Technologies • Bengaluru

On-site
INR 1,000,000 - 1,300,000
Senior AI/ML Engineer
Senior AI/ML Engineer

Staples India • Chennai District

On-site
INR 1,800,000 - 3,600,000