AI Architect

LatentBridge; Pune District; On-site; INR 4,000,000 - 8,000,000; Full time

Job summary

LatentBridge seeks an experienced AI Architect to lead end-to-end design, productionisation and operationalisation of LLM-based solutions on Azure. You will own architecture, deployment and scalable delivery for a high-visibility R&D project in financial data intelligence, while guiding a cross-functional team.

You will drive MLOps pipelines, model governance and retrieval systems, collaborating with security and data teams to ensure robust, compliant solutions for clients.

Qualifications

• 12+ years in software engineering/AI with hands-on production experience.
• Deep experience with LLMs and RAG architectures: retrieval design and embeddings.
• Proven track record in fine-tuning/customising LLMs (LoRA, full-fine tune) and prompt engineering.
• Strong Azure AI stack experience: Azure OpenAI/GPT, Azure ML, AKS, Data Factory/Synapse.
• Expertise in Agentic frameworks and orchestration (LangChain, LangGraph).
• Production MLOps/ModelOps: CI/CD for models, monitoring, drift detection.

Responsibilities

• Architect and build Agentic AI systems: orchestrate agents, action executors, retrieval layers, and feedback loops.
• Design and implement LLM solutions (RAG, retrieval chains, prompt engineering) for production use.
• Own model deployment, serving and scaling on Azure and hybrid setups.
• Build MLOps pipelines: CI/CD for models, automated testing, monitoring and drift detection.
• Lead data pipelines for retrieval: vector stores, semantic search, embeddings, data privacy controls.
• Implement model explainability, safety and governance: prompts, checks and audit trails.
• Collaborate with product, security, DevOps and UX for integrated delivery and acceptance.
• Mentor engineers; conduct technical reviews; recruit when required.
• Act as primary technical contact for clients: present designs and support RFPs.

Skills

LLM architectures

Azure stack

Python

MLOps

Kubernetes

Security & compliance

Data engineering basics

English communication

Tools

Pinecone

Weaviate

Milvus

LangChain

LangGraph

Azure ML

AKS

Docker

Job description

Job Title: AI Architect

Location: India – Pune, Bangalore

Experience Required: 12+ years

Engagement: [Full-time]

Project Type: High-visibility R&D initiative in financial research & data intelligence

Job Summary

We are seeking an experienced, hands‑on AI Architect (12+ years) to lead technical delivery and client engagement for Agentic AI platforms. The role owns end‑to‑end design, productionisation and operationalisation of LLM‑based solutions (RAG, fine‑tuning, model serving) on Azure, and will act as the technical face to the client while leading a cross‑functional delivery team.

What Success Looks like

• Deliver production Agentic AI features that meet SLA targets for latency, throughput and reliability.
• Reduce time‑to‑value for LLM integrations via repeatable patterns, MLOps pipelines and reusable components.
• Maintain model governance, explainability and security posture appropriate for sensitive data domains.

Key Responsibilities

• Architect and build Agentic AI systems: orchestrate agents, action executors, retrieval layers, and feedback loops.
• Design and implement LLM solutions (RAG, retrieval chains, prompt engineering, fine‑tuning/LoRA/P‑tuning) for production use.
• Own model deployment, serving and scaling on Azure (Azure AI, Azure ML, AKS, container registries) and hybrid setups.
• Build MLOps & ModelOps pipelines: CI/CD for models and services, automated testing, monitoring, drift detection and rollbacks.
• Lead data pipelines for retrieval: vector stores, semantic search, indexing, embeddings, data privacy & access controls.
• Implement model explainability, confidence scoring, adversarial protections and prompt security (prompt injection mitigation).
• Define and enforce model governance: versioning, reproducibility, lineage, audit trails and compliance.
• Collaborate with product, data engineering, security, DevOps and UX to ensure integrated delivery and acceptance.
• Mentor and upskill engineers; conduct technical reviews and pair programming; recruit when required.
• Act as primary technical contact for clients: present designs, lead architecture reviews, and support RFP/interview processes.

Required Skills & Experience

• 12+ years in software engineering/AI with demonstrable, hands‑on production experience.
• Deep experience with LLMs and RAG architectures: retrieval design, vector DBs (Pinecone/Weaviate/Milvus), embeddings.
• Proven track record in fine‑tuning/customising LLMs (LoRA, full‑fine tune, instruction tuning) and prompt engineering.
• Strong Azure AI stack experience: Azure OpenAI/GPT, Azure ML, AKS, Azure Functions, KeyVault, Data Factory/Synapse.
• Expertise in Agentic frameworks and orchestration (LangChain, LangGraph, custom agent frameworks).
• Production MLOps/ModelOps: CI/CD for models, model registry, automated testing, monitoring (Prometheus/Grafana/ELK), drift detection.
• Backend engineering: Python, FastAPI, microservices, Docker, Kubernetes, gRPC/REST, event-driven architectures.
• Data engineering basics: SQL/NoSQL, ETL, schema design, data privacy controls.
• Security & compliance: secrets management, access controls, vulnerability remediation, data encryption in transit & at rest.

Good‑to‑Have Skills

• Experience with hybrid/multi‑cloud deployments and avoiding provider lock‑in.
• Familiarity with LangGraph, agentic safety patterns, and adversarial robustness testing.
• Prior exposure to financial data or private markets / regulated data handling.
• Experience with model explainability tools (SHAP, LIME, integrated gradients) and bias/fairness testing.
• Familiarity with Terraform/ARM for infra as code and GitOps workflows.