AI Developer

Agentic AI Systems & LLM Pipeline Engineering

About the Role

We are building a production-grade, multi-agent AI platform designed for high-stakes, regulated environments. This role sits at the heart of that engineering effort responsible for designing, building, and maintaining the agentic pipeline, LLM integration layer, prompt engineering framework, and deterministic tooling that powers the platform's core capabilities.

This is not a research role and not a data science role. You will be writing production code that AI agents execute against real enterprise data in heavily regulated financial institutions. Precision, reliability, and auditability are non-negotiable.

What You Will Build

CORE AGENTIC PIPELINE

- Design and implement multi-agent orchestration pipelines coordinating sequences of specialised AI agents across a structured, multi-stage workflow
- Implement Human-in-the-Loop (HITL) workflow engine stateful approval gates where named human reviewers must approve, edit, or reject AI outputs before pipeline advancement
- Ensure all agents are stateless between sessions — no cross-session memory accumulation, no passive learning from runtime data

LLM INTEGRATION & PROMPT ENGINEERING

- Build and maintain the Model Abstraction Layer — decoupling agent logic from specific model versions to enable zero-downtime model upgrades
- Engineer sophisticated multi-turn system prompts encoding domain knowledge, evaluation criteria, output structure requirements, and adversarial review logic
- Implement RAG (Retrieval Augmented Generation) pipelines using embedding models for semantic document retrieval — context window management, chunking strategy, and retrieval precision optimisation
- Manage model inference parameters (temperature, top-P, top-K, max tokens) per agent role — balancing output consistency and quality
- Integrate with Azure OpenAI (GPT-5.5, GPT-5.4, text-embedding-3-large) and/or Vertex AI (Gemini 2.0 Pro, Gemini 2.0 Flash, text-embedding-gecko) via managed API endpoints

DETERMINISTIC TOOLING

- Build and maintain the deterministic tool layer — conventional software components (database queries, REST API calls, file parsers, data validators, schema normalisers) that handle all evidence retrieval and data access with exact, auditable, reproducible results




- Implement read-only service account integrations with enterprise source systems
- Design and implement evidence validation logic — completeness thresholds, exception handling, missing evidence escalation procedures

SECURITY & INFRASTRUCTURE

- Implement offline RSA-4096 JWT-based license enforcement — cryptographic license validation without network dependency
- Build immutable audit trail logging — every agent action, HITL decision, evidence retrieval, and output version logged in structured, tamper-evident form
- Containerise all components for Kubernetes deployment (AKS / GKE) — Helm chart authoring, Blue-Green deployment support

Required Skills & Experience

AI / LLM ENGINEERING — ESSENTIAL

- 3+ years building production LLM-integrated applications — not prototypes or notebooks, but shipped systems handling real data
- Deep expertise in agentic AI patterns — ReAct loops, tool use, multi-agent orchestration, agent memory and state management
- Hands-on prompt engineering at production scale — system prompt design, few-shot construction, chain-of-thought, structured output enforcement, adversarial/critic prompt patterns
- RAG implementation experience — embedding models, vector databases (pgvector, Pinecone, Weaviate, or equivalent), semantic chunking, retrieval evaluation
- Proficiency with Azure OpenAI SDK and/or Vertex AI SDK — model invocation, streaming, error handling, retry logic, token management
- Understanding of LLM failure modes — hallucination, confidence calibration, context window limits, prompt injection — and architectural mitigations for each

SOFTWARE ENGINEERING — ESSENTIAL

- Expert-level Python — async programming, Pydantic data models, structured output parsing, robust error handling
- REST API design and integration — building and consuming enterprise APIs (OpenAPI spec, authentication patterns, rate limiting, retry logic)
- Relational database development — PostgreSQL / Cloud SQL schema design, query optimisation, transaction handling




- Cloud-native development on Azure or GCP — containerisation (Docker), Kubernetes (AKS/GKE), managed services (object storage, key vault/secret manager, monitoring)
- Git-based development workflow — trunk-based development, code review, CI/CD pipeline integration

SECURITY & COMPLIANCE AWARENESS — KEY

- Experience building within security-constrained environments — understanding of encryption at rest/in transit, secrets management, principle of least privilege, audit logging requirements
- Familiarity with confidential computing concepts (SGX enclaves, AMD SEV, or equivalent) — not required to be a specialist, but must understand the deployment constraints
- Understanding of data residency requirements and BYOC (Bring Your Own Cloud) deployment models

Strong Advantages

- Experience deploying AI systems in regulated financial services
- Experience with LangChain, LlamaIndex, AutoGen, or comparable agentic frameworks — and importantly, knowing when NOT to use them
- Background in MLOps / LLMOps — model versioning, Blue-Green model deployment, regression testing pipelines for model updates
- Experience with Azure Confidential Computing (DCv3 / Intel SGX) or GCP Confidential VMs
- TypeScript / Node.js as a secondary language

What We Are Looking For

Technical depth is necessary but not sufficient. The systems you will build are deployed in regulated financial institutions where a hallucinated finding or a broken audit trail has real consequences. We are looking for engineers who understand that production reliability and architectural precision are as important as model performance — and who take both seriously.

You should be comfortable with ambiguity in the problem space ("how should this agent reason about this edge case?") and intolerant of ambiguity in the solution space ("the audit trail must be complete and immutable — no exceptions").

What We Offer

- Work on one of the most technically demanding AI engineering problems in financial services — governed agentic systems in regulated environments
- Small team, high ownership — you will design and own major components, not implement tickets
- Exposure to cutting-edge model capabilities (GPT-5.5, Gemini 2.0 Pro) in production, against real enterprise data

More Info :- [email protected]

📌 Artificial Intelligence Developer (Noida)
🏢 NLB Services
📍 Noida