Job Description: Key Responsibilities

1. Agentic Solution Architecture & Design Authority

- Lead discovery and solutioning with stakeholders; translate business objectives into target-state agentic AI architectures, blueprints, and roadmaps .

- Own end-to-end solution design : multi-agent orchestration, tool-using agents, human-in-the-loop patterns, memory and state management, RAG and knowledge layers, and enterprise integration.

- Drive build vs. buy vs. partner decisions for models, agent frameworks, and solution with EXL standards.

2. Architecture Standards, Governance & Responsible AI

- Define and enforce reference architectures, design standards, and reusable patterns for agentic AI solutions across accounts.

- Embed security, privacy, compliance, and responsible AI – including agent guardrails, evaluation frameworks, and auditability – into every design.

- Conduct architecture and design reviews , ensuring solutions are scalable, cost-productive, and production-grade.

3. Technical Leadership Through Delivery

- Guide Forward Deployment Engineers, data scientists, and delivery teams from design through production – remaining hands-on at critical points (prototyping, integration, performance tuning).

- De-risk delivery by resolving complex technical blockers : legacy integration, agent reliability, model performance, and latency/cost/quality trade-offs.

- Ensure solutions move beyond POCs to enterprise-wide adoption and value realization .

4. Stakeholder Engagement & Advisory

- Act as trusted technical advisor to CIOs, CDOs and enterprise architects; lead architecture workshops, design authority boards, and executive briefings.

- Support pre-sales and strategic deals : solution shaping, effort estimation, technical proposals, and orals.

- Articulate architecture decisions in business terms – value, risk, cost, and time-to-market.

5. Capability Building & Reuse

- Convert engagement learnings into reusable assets, accelerators, and reference implementations for EXL’s agentic AI portfolio.

- Mentor architects and senior engineers; raise the architecture bar across the Enterprise AI practice.

- Continuously track and translate emerging AI advances (Agentic AI, LLMs, autonomous systems) into EXL-ready architecture strategies.

Technical & Architecture Expertise (Agentic AI)





- Multi-agent system design : supervisor–worker hierarchies, planner–executor and reflection loops, blackboard and swarm patterns; task decomposition, delegation, and inter-agent communication protocols; deciding when a single-agent vs. multi-agent topology is architecturally justified.

- Agent state, memory & context engineering : short-term vs. episodic vs. semantic memory design, checkpointing and resumability, durable execution for long-running agents; context-window budgeting, compaction/summarization strategies, and retrieval-augmented context assembly.

- Framework and protocol depth : LangGraph (graph state machines, interrupts, human-in-the-loop nodes), CrewAI, AutoGen/Semantic Kernel; MCP (Model Context Protocol) for tool and resource federation and A2A for agent interoperability; sound judgment on custom orchestration vs. framework adoption.

- Model strategy & token economics : model portfolio design and routing (frontier LLMs vs. SLMs), structured outputs and function-calling schema design, constrained decoding; fine-tuning vs. RAG vs. prompt-optimization trade-offs; prompt caching, batching, distillation, and quantization to hit latency and cost SLOs.

- Retrieval & knowledge architecture : hybrid retrieval (sparse + dense), rerankers, GraphRAG and knowledge graphs; chunking and embedding strategy, freshness pipelines, and access-control-aware retrieval (document/row-level security) for regulated enterprises.

- Evaluation architecture : golden datasets, LLM-as-judge with calibration, trajectory-level agent evals, regression harnesses wired into CI/CD gates, and online canary/A-B evaluation for continuous quality assurance.

- Guardrails, safety & governance : prompt-injection and jailbreak defenses, PII detection/redaction, policy engines, sandboxed tool execution, human-approval gates for high-risk actions, and full audit trails/lineage for responsible AI and regulatory compliance.





- Production & platform architecture : model gateways, multi-tenancy, VPC/private endpoints, HA/DR, autoscaling, rate limiting, and circuit breakers; observability via distributed tracing (OpenTelemetry), token/cost telemetry, and drift monitoring at enterprise scale.

- Enterprise integration : event-driven and API-led integration patterns, identity propagation (OAuth/OIDC), secrets management, and integrating agents with CRM, contact center, workflow platforms, and legacy estates.

- Multimodal & emerging stacks : voice agents (streaming ASR/TTS – e.g., ElevenLabs), avatar/video (HeyGen), computer-use agents; fluency with AI-native tooling (Claude Code, Cursor) and evolving OpenAI/Anthropic platform capabilities.

- Responsibilities: Robust, scalable agentic architectures that move engagements from POC to enterprise-wide production adoption.

- Reference architectures, patterns, and accelerators reused across multiple accounts – reducing time-to-value and delivery risk.

- Tangible business outcomes (productivity, cost, quality, revenue) enabled by sound architecture decisions.

- Strong security, compliance, and responsible AI posture across all designed solutions.

Recognized technical credibility with CTO/CIO organizations, contributing to account growth and strategic deal wins.

- Qualifications: 12+ years of experience in software/solution architecture, data, or digital transformation, with 3+ years architecting AI/LLM or agentic AI solutions .

- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.

- Proven track record of:

- Architecting and delivering production AI/GenAI solutions for large enterprise clients

- Serving as design authority across multiple concurrent engagements or programs

- Operating in business-facing, consulting, or forward-deployed environments with senior stakeholders

- Strong understanding of:

- Agentic AI and LLM architectures , RAG, evaluation, and guardrails

- Data platforms, cloud, security, and compliance

- Enterprise integration and legacy modernization

- Experience engaging with CTOs, CIOs, enterprise architects, and executive stakeholders .

Willingness to travel and work onsite at business locations as required.

📌 Assistant Vice President (Delhi)
🏢 EXL Service
📍 Delhi