About the Role:
We are seeking an AI Native Engineer with proven hands-on experience building enterprise business applications and agentic AI solutions in production. The role requires strong technical depth across AI-augmented software development and application security. You will work alongside an experienced in-house AI expert and are expected to contribute at a peer level.
Key Responsibilities: - Design and deliver production-grade business applications with AI natively integrated into the architecture.
- Build and operate Agentic AI systems — multi-step, autonomous pipelines using frameworks such as LangGraph, AutoGen, CrewAI, or equivalent.
- Drive AI SDLC practices across the development lifecycle — AI-assisted code generation, review, testing, documentation, and CI/CD augmentation.
- Apply application security expertise in both traditional and AI-specific contexts.
- Evaluate and integrate emerging AI tools and frameworks with sound engineering judgment.
Required Qualifications: - AI Native Engineering
- Production experience with end-to-end AI-powered business applications.
- Proven expertise in Agentic AI architectures — tool-use, memory management, multi-agent orchestration, and human-in-the-loop workflows.
- Hands-on across AI SDLC use cases — AI-driven code review, automated test generation, intelligent QA pipelines, and AI-powered requirements analysis.
- Proficiency with LLM APIs (OpenAI, Anthropic, Azure OpenAI, or open-source equivalents), RAG pipelines, vector databases, and embedding strategies.
Application Security: - Solid experience in traditional application security — OWASP Top 10, secure coding, SAST/DAST, API security, and threat modeling.
- Hands-on with AI-specific security risks — prompt injection, RAG poisoning, model data leakage, and adversarial inputs.
- Familiarity with OWASP LLM Top 10, NIST AI RMF, MITRE ATLAS.
Programming Languages (Minimum one, ideally two): - Java — Enterprise applications, Spring Boot, microservices, AI SDK integration.
- C — Systems-level development, AI inference engine integration (ONNX, TensorRT, llama.cpp).
- Python — LLM orchestration (LangChain, LangGraph, AutoGen), data pipelines, FastAPI.
Experience: - 7–12 years of overall software engineering experience.
- 3–5 years in AI/ML engineering with at least 2 years in Generative AI and Agentic AI in production.
Nice to Have: - AI integration with enterprise platforms (ERP, CRM, DevSecOps toolchains).
- LLM observability and evaluation (RAGAS, DeepEval, Promptfoo).
- AI governance, responsible AI, and explainability in enterprise contexts.
- Open-source contributions or published technical content.
|
