AI Engineer - Agentic AI / GenAI at Secninjaz, Delhi
Open. Posted .
Agentic AI engineering for a GRC platform, spanning multi-agent workflows, RAG, secure APIs and production deployment. The role is full-time in Delhi.
Applying opens the employer's page. Want jobs like this sent to you each morning? Open Elip.
| Location | Delhi, Delhi |
|---|---|
| Work mode | On-site |
| Experience | 2–4 years |
| Job type | Full-time |
| Pay | Not stated by the employer |
| Role | AI Engineer |
| Skills asked for | Python, FastAPI, REST APIs, Asynchronous programming, PostgreSQL, Redis, LangGraph, LangChain |
| Posted | 18 Nov 2026 |
Elip's summary
Builds agentic AI applications for a team developing an AI-native Governance, Risk, and Compliance platform. Develops multi-agent orchestration, RAG pipelines, and secure backend services using LangGraph, LangChain, and Python. Deploys production applications on AWS and applies Docker.
The job, in the employer's words
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.
About Secninjaz
Headquartered in Delhi, founded in 2016.
- People in Elip's index who work here
- 59
- Typical time at Secninjaz
- 11 months
- Typical career length so far
- 3.8 years
Totals from public professional profiles in Elip's index; any group under ten people is left out.
Similar open jobs
About this page
Elip lists jobs that employers publish on their own careers sites, never copies from job boards. This one comes from Secninjaz's listing on Zoho, posted 18 Nov 2026. The summary is Elip's; the description is the employer's. When the job closes, this page says so.