Senior AI Developer – InfraSec Automation (L2)

Theomnihire; Mumbai; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Theomnihire seeks a Senior AI Developer – InfraSec Automation (L2) to design, build, and deploy production-grade, LLM-powered security features. You will develop end-to-end RAG pipelines, agentic workflows, and automated remediation tools within the Cyber Security Division, writing Python and Java, and integrating AI into security platforms and cloud infra.

You will implement guardrails, evaluation harnesses, and scalable microservices, collaborating with cross-functional teams to translate

Qualifications

• 4–6 years of core software engineering and AI development experience.
• Hands-on experience with LLM APIs and frameworks; building production-grade AI features.
• Experience with security-focused AI controls and CI/CD pipelines.
• Knowledge of RAG, embeddings, vector stores, and evaluation tooling.

Responsibilities

• Design, build, and deploy LLM-powered AI features for infrastructure security.
• Develop prompt templates, system prompts, and structured-output schemas.
• Implement end-to-end RAG pipelines with embeddings and vector stores.
• Create Python microservices and APIs (FastAPI/Flask) integrating LLM providers.
• Develop evaluation harnesses to measure accuracy and latency.
• Implement AI guardrails, including prompt-injection mitigations and PII redaction.
• Integrate AI services with security scanners, SIEMs, and monitoring stacks.
• Support CI/CD automation and MLOps pipelines.

Skills

Python

LLM Frameworks & APIs

Vector Databases & RAG

LLM Evaluation & Tooling

Infrastructure & Web

Education

B.Tech in CS/IT/AI/ML

M.Tech in CS/IT/AI/ML

Certifications: CISSP

Certifications: CCSP

Certifications: AZ-500

Certifications: Azure AI Engineer Associate (AI-102)

Certifications: AWS Certified Security – Specialty

Certifications: Google Professional Cloud Security Engineer

Tools

FastAPI/Flask

LangChain

LlamaIndex

Pinecone

Weaviate

FAISS

Docker

CI/CD

Azure/AWS/GCP

Job description

Senior AI Developer – InfraSec Automation (L2)

Job Title: Senior AI Developer – InfraSec Automation (L2)

Working Hours: 9:00 AM – 6:00 PM

Mode of Interview: Face-to-Face or MS Teams

Headcount: 2 Positions

Position Summary

The Senior AI Developer – InfraSec Automation (L2) is a hands‑on technical role focused on designing, building, and deploying production‑grade, LLM‑powered features and AI tools for infrastructure security workflows. Working within the Cyber Security Division, you will bridge AI engineering and security operations by developing end‑to‑end RAG pipelines, agentic workflows, automated remediation assistants, and evaluation harnesses. You will write production‑quality Python and Java code, implement security controls around AI services, and integrate automated AI capabilities natively into security platforms, SIEMs, and cloud infrastructure.

Requirements

Key Responsibilities

AI Feature Development: Design, build, and ship LLM‑powered security assistants that support vulnerability summarization, log triage, remediation recommendations, policy reviews, and natural‑language queries over security data.

Prompt Engineering & Schemas: Develop prompt templates, system prompts, and structured‑output schemas (JSON schema, function calling), continuously iterating via offline and online evaluations.

End‑to‑End RAG Pipelines: Implement Retrieval‑Augmented Generation (RAG) pipelines including chunking strategies, embeddings management, vector store integration, retrieval tuning, and grounding.

Microservices & API Development: Build and operate Python‑based AI microservices and APIs (using FastAPI/Flask) that wrap LLM providers (Anthropic, OpenAI, Azure OpenAI, Vertex AI) and open‑source models, alongside supporting backend services in Java where required.

LLM Evaluation & Quality Control: Implement evaluation harnesses, golden datasets, and regression suites to measure LLM performance, tracking accuracy, hallucination rates, latency, and API cost.

AI Security & Guardrails: Apply responsible‑AI controls including prompt‑injection mitigations, PII redaction, output filtering, rate limiting, audit logging, and access controls.

Ecosystem Integrations: Connect AI services with security scanners, ticketing platforms, SIEMs, and monitoring stacks to deliver actionable, automated security workflows.

Automation & MLOps: Automate data preparation, embedding refreshes, eval runs, and health checks using Python, Shell scripts, Git, Docker, and CI/CD pipelines.

Cross‑Functional Collaboration: Partner with security, DevOps, infrastructure, and engineering teams to translate complex security requirements into scalable AI solutions.

Candidate Profile & Qualifications

Experience: 4–6 years of core software engineering and AI development experience.

Education: B.Tech or M.Tech in Computer Science, Information Technology, AI/ML, or a related field.

Core Technical Skills:

Python & Backend: Strong Python (FastAPI/Flask, async patterns, packaging, testing); working knowledge of Java for backend REST APIs.

LLM Frameworks & APIs: Hands‑on experience with LLM provider APIs (Anthropic, OpenAI, Azure OpenAI, Vertex AI) and frameworks (LangChain, LlamaIndex, LangGraph, or Haystack).

Vector Databases & RAG: Practical experience with vector stores (pgvector, Pinecone, Weaviate, Chroma, FAISS, Azure AI Search, or Vertex AI Vector Search).

LLM Evals & Tooling: Experience building evaluation sets using frameworks like RAGAS, DeepEval, Promptfoo, or LangSmith.

Infrastructure & Web: Linux/Shell scripting, Docker, Git, CI/CD, basic HTML/CSS/JS, and experience with at least one major cloud platform (Azure, GCP, or AWS).

Certifications (Any one required):

CISSP, CCSP, AZ-500, Azure AI Engineer Associate (AI-102), AWS Certified Security – Specialty, or Google Professional Cloud Security Engineer.

(Desirable: CISM, CEH, OSCP, Google PMLE, AWS ML Specialty, CKA, Terraform Associate, or SC-100).