AI Engineer - Agentic AI / GenAI (Delhi)

AI Engineer - Agentic AI / GenAI (Delhi)

19 Nov
|
Secninjaz
|
Delhi

19 Nov

Secninjaz

Delhi

Job Information

- Date Opened 11/18/2026
- Job Type Full time
- Industry IT Services
- City Delhi
- State/Province Delhi
- Country India
- Zip/Postal Code 110034

About Us

SecNinjaz is renowned for providing world-class IT services and cybersecurity solutions globally. Founded in 2018, SecNinjaz has evolved into a leading cybersecurity force, combining the agility and innovation of a startup with the expertise and depth of seasoned professionals. We serve clients across various industries, including Healthcare, Fintech, Manufacturing, Telecom, Infrastructure, and e-commerce. Our solutions are always customised, future-ready, and designed to blend technical excellence, innovation, and a deep commitment to protecting the digital world.

Secninjaz Technologies | AI Engineering Resource Profile 1 AI Engineer - Agentic AI / GenAI

Company: Secninjaz Technologies | Project: Agentic Native GRC Platform

Experience: 2-4 years preferred; relevant hands-on production experience is essential | Type: Full time

About the Project

We are building an AI-native Governance, Risk, and Compliance (GRC) platform that uses specialized AI agents to automate compliance workflows, evidence collection, policy management, assessments, continuous monitoring,

and audit readiness. The platform emphasizes governed execution, verifiable evidence, secure integrations, and reliable production operations.

Role Overview The AI Engineer will work closely with the existing AI engineering team on architecture, development, testing,

deployment, and continuous improvement. We seek a collaborative, self-driven engineer who takes ownership of assigned components and contributes practical experience in shipping reliable AI applications to production. This document describes a resource profile; staffing or hiring decisions remain with management.

Key Responsibilities





- Collaborate on the design and implementation of scalable multi-agent workflows using LangGraph, LangChain,

and LLM APIs.
- Build specialized AI agents, tool-calling integrations, agent memory, orchestration, and human-in-the-loop

workflows.
- Develop RAG pipelines, document intelligence, retrieval, and evidence-processing capabilities.
- Implement secure backend services and APIs with Python, FastAPI, PostgreSQL, and Redis.
- Integrate enterprise APIs and systems; apply authorization, tenant isolation, and secure agent execution.
- Contribute to LLM evaluations, guardrails, observability, performance optimization, and failure recovery.
- Work with the team to containerize, deploy, monitor, and maintain a production-ready MVP on AWS.
- Participate in technical design discussions, code reviews, debugging, and incident resolution; own assigned

modules end-to-end. Required Technical Skills & Qualifications
- Backend: Strong Python, FastAPI, REST APIs, asynchronous programming, PostgreSQL, and Redis.
- Agentic AI: Practical LangGraph and LangChain experience; multi-agent orchestration, LLM tool/function calling,

MCP integrations, memory, and human-in-the-loop patterns.
- GenAI & retrieval: LLM APIs, prompt engineering, RAG, embeddings, and vector databases such as FAISS or

ChromaDB.
- Cloud & delivery: Hands-on AWS deployment, Docker, CI/CD, environment configuration, and production

monitoring; familiarity with ECS/Fargate, RDS, S3, SQS, and CloudWatch.
- Production track record:



Significant hands-on contribution to at least one successfully deployed AI/GenAI MVP

or application, including debugging and operational support.
- Reliability & observability: Logging, monitoring, workflow retries, fault tolerance, failure recovery, LLM

evaluation, LangSmith or equivalent tooling, and cost optimization.
- Security: Prompt-injection mitigation, controlled tool execution, authentication, authorization, secure APIs, and

tenant data isolation. Secninjaz Technologies | AI Engineering Resource Profile 2
- Enterprise engineering: Experience with enterprise SaaS products or compliance automation platforms and

integration with external systems.

Professional Expectations

- Ownership: Accountable for assigned deliverables from design through tested production delivery.
- Collaboration: Works effectively with the team, communicates blockers early, participates in decisions, and

shares knowledge.
- Initiative: Identifies issues proactively and proposes solutions without requiring constant supervision.
- Engineering judgment: Balances speed with maintainability, security, reliability, and measurable outcomes.

Mandatory Screening Criteria
- Demonstrable experience building Agentic AI / GenAI applications and implementing agent orchestration.
- Direct, meaningful involvement in a successful production deployment of an AI-powered application.
- Practical AWS and Python backend development experience, including API integration.
- Ability to clearly explain past production responsibilities, architecture choices, operational issues, and resolutions.
- Evidence of ownership of technical components and effective teamwork.

Expected Outcome Collaborate with the existing team to develop, deploy, and operate a secure, scalable, production-ready Agentic

Native GRC MVP, while taking clear responsibility for assigned technical components.

📌 AI Engineer - Agentic AI / GenAI (Delhi)
🏢 Secninjaz
📍 Delhi

Reply to this offer

Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.

Subscribe to this job alert:

Get the latest job offers by email for: ai engineer - agentic ai / genai (delhi) / delhi

Subscribe to this job alert:

Get the latest job offers by email for: ai engineer - agentic ai / genai (delhi) / delhi