FDE-Agentic AI

C5i; Bengaluru; On-site; INR 1,800,000 - 3,500,000; Full time

Job summary

C5i is seeking a Forward Deployed Engineer to build production-grade agentic systems for regulated enterprise clients in Bengaluru. You will work embedded with client squads, handling client data and infrastructure with a focus on security and reliability.

The role requires hands-on Python, cloud expertise, and 4–6 years of experience. You will guide AI coworkers, validate their outputs, and ensure delivery meets required quality standards.

Qualifications

• Hands-on Python development in production systems.
• Experience with agentic AI tools and multi-agent workflows.
• Understanding of RAG architectures and prompt evaluation.

Responsibilities

• Build production-grade agentic systems on cloud platforms.
• Design multi-agent workflows, RAG pipelines, and tool integrations.
• Write evaluations and define success criteria for performance.
• Integrate solutions into regulated enterprise environments with security constraints.
• Own code quality, testing, docs, and production support.
• Practice DevSecOps including CI/CD, IaC, secrets, IAM, observability
• Contribute reusable IP and deployment runbooks
• Stay updated with AI lab developments and frontier releases
• Collaborate with client technical teams during design reviews

Skills

Python programming

Agentic AI frameworks

RAG architectures

Vector databases

CI/CD

Security best practices

Ambiguity tolerance

Strong mathematical/CS foundation

Education

CS/Engineering/Math/Physics degree

Tools

LangGraph

LangChain

CrewAI

Job description

We are seeking a Forward Deployed Engineer (Agentic AI) to build and deploy production-grade agentic systems for regulated enterprise clients. This role is embedded within client squads and involves working directly on client infrastructure and with client data in complex, security-conscious environments.

The ideal candidate is a strong engineer with hands-on experience in Python, cloud technologies, and agentic AI systems. This role is open to exceptional engineers with 4-6 years of experience. We value strong technical judgment, curiosity, ownership, and practical experience building with agentic tools.

The candidate will work alongside AI coworkers as part of your development process. You will direct, review, and validate their output to move faster while maintaining quality, reliability, and control.

Key Responsibilities

• Build production-grade agentic systems on cloud platforms and enterprise AI platforms
• Design and implement multi-agent workflows, RAG pipelines, tool integrations, MCP servers, and human-in-the-loop systems
• Write evaluations before features and define clear success criteria for system performance
• Integrate solutions into regulated enterprise environments with real security, access, and data constraints
• Own code quality, testing, documentation, and production support
• Practice DevSecOps from day one, including CI/CD, infrastructure as code, secrets management, IAM, and observability
• Contribute reusable IP such as code modules, evaluation frameworks, deployment runbooks, and design patterns
• Stay current with developments across cloud platforms and the broader agentic AI ecosystem, including leading AI labs and frontier releases
• Work closely with client technical teams and represent your work clearly in design reviews and discussions
• Use AI coworkers effectively as part of the delivery process while maintaining engineering judgment and accountability

Mandatory Skills

• Strong programming fundamentals in Python
• Hands-on experience with agentic AI frameworks such as LangGraph, LangChain, CrewAI, or equivalent
• Understanding of RAG architectures, vector databases, prompt engineering, and evaluation harnesses
• Working knowledge of CI/CD, testing, infrastructure as code, and security best practices
• Strong problem-solving ability and comfort working in ambiguous environments
• Strong academic background in computer science, engineering, mathematics, or physics

Good to Have Skills

• Experience with TypeScript, Java
• Cloud certifications relevant to your platform experience
• Experience building production agentic systems for regulated enterprises
• Experience with DevSecOps, observability, and enterprise security constraints
• Ability to use AI tools effectively as part of the development process
• Experience creating reusable technical assets for future teams
• Exposure to leading AI labs and open-source frontier work
• Familiarity with multi-agent orchestration, MCP servers, and human-in-the-loop workflows