Application Architect - GenAI

This is a role for a builder-architect: a seasoned application architect who has upskilled into a hands-on GenAI practitioner - someone who still writes code, has put agentic and GenAI-based solutions into live environments, and can translate AI-led engineering strategy into executable delivery models for customer stakeholders across time zones.

Key Responsibilities

1. GenAI Solution Architecture & SDLC Acceleration

- Define the target-state architecture and adoption roadmap for AI-led SDLC: where and how AI agents participate in planning, coding, review, testing, and deployment phases.

- Extend agents upstream into engineering design: spec-driven development (specs and design documents as the source of truth agents implement against), AI-assisted architecture documentation, and agent reviewers in design and code-review gates.

- Architect end-to-end GenAI solutions for the customer - agentic developer workflows, RAG pipelines, LLM-based applications - and scale successful patterns from pilot to production.

- Lead architecture transformation accelerated by AI - core/legacy modernization and new event-driven architecture (EDA) implementations - using agents for code comprehension, documentation, migration, functional-equivalence test generation, and event schema/handler scaffolding.

- Design AI-enabled business workflows with humans in the loop: document intake and extraction, confidence thresholds and exception routing, reviewer feedback loops, and end-to-end auditability.

- Enable and coach developer squads on agent-assisted engineering; define working practices, quality gates, and guardrails for AI-generated code.

- Lead a team of GenAI engineers delivering these solutions - setting technical direction, reviewing designs, and growing the team's agentic engineering capability.

- Measure and report acceleration outcomes: cycle time, throughput, quality, and adoption metrics - and iterate the blueprint based on evidence.

- Define and enforce architecture standards, design patterns, and responsible-AI practices (security, data privacy, auditability) for GenAI systems; operate architecture governance - design authority, decision records, and reviews - across delivery teams.

- Establish evaluation and guardrails as first-class engineering: evaluation harnesses and golden datasets, hallucination and regression checks, output guardrails, and production monitoring for GenAI systems.

2. Agentic Engineering & Tooling (hands-on)

- Design multi-agent systems with defined roles - orchestrator, coder, reviewer, tester agents - including task routing, state management, and human-in-the-loop checkpoints.

- Hands-on configuration and governance of GenAI developer tooling at enterprise scale: agentic coding tools - CLI-driven coding agents and AI pair-programming solutions that go well beyond autocomplete-style copilots - including tool-server (MCP) setup, custom commands, hooks, and repository context/instruction files, plus agent SDKs and orchestration frameworks.

- Design and deploy MCP (Model Context Protocol) servers to expose the customer's tools, APIs, and data sources to AI agents; apply tool-use / function-calling patterns for LLM-driven agents.

- Select and integrate foundation models (e.g., Anthropic Claude, OpenAI GPT, Gemini) via APIs or managed platforms (AWS Bedrock, Azure OpenAI / AI Foundry, Google Vertex AI); design model-tiering and routing strategies - frontier reasoning models for complex work, fast lightweight models for high-volume steps, open-weight models (Llama, Mistral) where data residency requires - balancing capability, cost, and latency.

- Deploy and operate GenAI workloads within enterprise cloud estates: private endpoints and network isolation, identity and access management, quota / rate-limit and regional-availability planning, model gateways, and cost governance (token budgeting, caching, chargeback).

- Advanced retrieval patterns: GraphRAG / knowledge-graph-augmented retrieval, text-to-SQL over enterprise data.

3. Context Engineering & Domain Knowledge Capture

- Design and operate context engineering frameworks: repository instruction and context files, system prompts, retrieval strategies, context-window budgeting, and memory patterns - so agents carry accurate project, codebase, and domain context.

- Context engineering for business ontology: model the customer's domain as formal ontologies, taxonomies, and knowledge graphs - entities, relationships, and business rules - so agents reason over structured domain semantics, not just retrieved text.

- Model business processes as state machines: explicit lifecycle and state-transition models that let agents know where a case stands and which actions are legal - and deterministic state-machine orchestration to govern non-deterministic agent workflows.

- Capture and codify insurance domain knowledge: work with SMEs to elicit product structures, underwriting and claims rules, processes, glossaries, and regulatory constraints, and convert them into machine-usable assets - knowledge bases, taxonomies, RAG corpora, and golden datasets that ground agent output.

- Apply prompt engineering rigor: few-shot examples, chain-of-thought, structured output design, prompt versioning, and evaluation against golden datasets.

Required Qualifications

- 12-14 years of proven experience in technology leadership / principal or application architect roles on enterprise-scale, distributed multi-tier systems.

- Strong architecture pedigree: n-tier, microservices, and event-driven architecture (EDA) design - including messaging/streaming platforms (Kafka or cloud-native equivalents) - enterprise integration, API design and management, and cloud-native delivery on AWS, Azure, or GCP (IaaS/PaaS/SaaS, containers, CI/CD).

- Deep expertise in at least one major enterprise stack (Java/Spring, .NET, Python, or Node.js) with breadth across others; working proficiency in Python for GenAI development.

- Demonstrable agentic GenAI delivery: at least one agent-assisted engineering or LLM-based solution taken into production or a serious enterprise pilot - able to walk through the architecture, trade-offs, and measured outcomes.

- Practical, current knowledge of multi-agent design, MCP, RAG variants (hybrid search with re-ranking, agentic RAG, RAG over code and structured data), embeddings/vector search, prompt and context engineering, evaluation harnesses and guardrails, and LLM limitations (hallucination, context-window constraints, cost/latency, data privacy).

- Experience leading technology-driven programs - POCs, innovation initiatives, and solution asset development - through to large-scale delivery.

- Experience practicing Design Thinking and Systems Thinking in real-world scenarios.

- Outstanding client-facing communication: proven experience engaging customer stakeholders on requirements and delivery, and explaining complex technology in an easy-to-understand way.

LTIMindtree is proud to be an equal opportunity employer. We are committed to equal employment opportunity regardless of race, ethnicity, nationality, gender, gender-identity, gender expression, language, age, sexual orientation, religion, marital status, veteran status, socio-economic status, dis-ability or any other characteristic protected by applicable law.

Skills

Solution Design, Generative AI, IT Project Management, Large Language Model