Applied AI Engineer - Agentic Systems

2-6 years

Gurgaon / Hybrid

Applied AI Engineering

Role Summary

We are looking for a hands-on Applied AI Engineer to design, build, evaluate, and productionise Generative AI and agentic applications across our product and solution portfolio. The role is centred on AI application engineering: turning foundation models into reliable systems that can reason, use tools, retrieve information, collaborate across agents, and complete complex business workflows.

We are particularly interested in engineers who have built real multi-agent systems with explicit orchestration, state and context management, tool use, human-in-the-loop controls, evaluation, observability, and failure handling. You may have used frameworks such as LangGraph, LangChain, CrewAI, Pydantic AI, Google ADK, OpenAI Agents SDK, Claude Agent SDK, or comparable frameworks and developer tooling.

Key Responsibilities

- Design and build Generative AI applications, autonomous agents, and multi-agent systems that solve real business problems across industries.
- Design agent orchestration patterns including supervisors and worker agents, routing, delegation, planning, tool selection, state management, memory, retries, fallbacks, and human approval points.
- Build agents that interact safely with enterprise data and systems through APIs, functions, retrieval, databases, vector stores, MCP servers, and other governed tools.
- Work with leading foundation models and model APIs, selecting appropriate models and designing effective prompts, structured outputs, tool schemas, context strategies, and model fallbacks.
- Build evaluation harnesses and test suites for agent quality, task completion, tool selection, groundedness, safety, latency, cost, and regression detection.
- Implement tracing, logging, observability, feedback loops, guardrails, and debugging approaches that make complex agent behaviour understandable and supportable in production.
- Prototype rapidly using modern AI SDKs and coding agents, then turn successful prototypes into maintainable, secure, production-grade applications.
- Work with product, engineering, data, architecture, security, and client teams to integrate AI systems into real workflows and enterprise environments.
- Continuously evaluate new models, agent frameworks, protocols, and development patterns, and turn useful capabilities into reusable engineering components.

What We're Looking For

We care more about evidence that you have built and debugged working AI systems than about a particular job title. Strong software engineering and AI application fundamentals are the priority.
- Approximately 2-6 years of software, ML, AI, or product engineering experience, including meaningful hands-on work with Generative AI or LLM-powered applications.
- Strong Python programming skills and good software engineering fundamentals, including APIs, asynchronous programming, testing, Git, packaging, and debugging.




- Solid understanding of LLM concepts including tokens and context windows, system and user prompts, structured outputs, tool/function calling, embeddings, retrieval, model selection, temperature and sampling, latency, and inference cost.
- Hands-on experience building agents or multi-agent systems using at least one modern framework such as LangGraph, LangChain, CrewAI, Pydantic AI, Google ADK, OpenAI Agents SDK, Claude Agent SDK, Microsoft Agent Framework, or similar.
- Experience implementing explicit agent orchestration rather than only prompt chains or chatbots, including state, routing, delegation, tool permissions, retries, checkpoints, and failure recovery.
- Experience with RAG and grounding patterns using enterprise documents, structured data, vector search, semantic search, or knowledge stores.
- Experience integrating LLM applications with external APIs, business systems, databases, and developer tools; familiarity with MCP is valuable.
- Understanding of AI evaluation techniques, including task-based evals, LLM-as-judge where appropriate, deterministic checks, test datasets, tracing, and regression testing.
- Understanding of production concerns including prompt injection, data leakage, access control, secrets, rate limits, token budgets, latency, reliability, observability, and cost management.
- Ability to investigate ambiguous model or agent failures systematically and improve behaviour through changes to prompts, context, tools, orchestration, models, or application logic.

Agentic AI Experience

- Built a multi-step or multi-agent system in which multiple specialised agents coordinate through an orchestrator, supervisor, graph, workflow, or shared state.
- Experience designing tool-using agents that take actions rather than only generate text, with controls around what each agent can access and execute.
- Familiarity with modern agent development environments and AI coding tools such as Google ADK, OpenAI Codex, Claude Code, and related SDKs or command-line development workflows.
- Experience with durable execution concepts such as checkpoints, resumability, idempotency, timeouts, retries, error routing, long-running tasks, and human-in-the-loop review.
- Experience instrumenting agent traces and using evaluations and production feedback to understand failure modes and improve solve rate, reliability, usefulness, and cost.
- Ability to explain the architecture of an agentic system end-to-end, including model choice, orchestration, state, memory, tools, identity, permissions, evaluation, monitoring, deployment, and operational support.

Nice to Have

- Experience building agentic solutions within Databricks or Snowflake,



including governed access to enterprise data, models, functions, or tools.
- Exposure to Databricks Unity Catalog, Model Serving, Vector Search, AI Gateway / Unity Gateway, or Snowflake Cortex Agents, Cortex Analyst, Cortex Search, and Cortex AI Gateway.
- Experience with MLflow, LangSmith, Langfuse, Arize Phoenix, OpenTelemetry, or similar evaluation and observability tooling.
- Experience with vector databases or search platforms such as Pinecone, Weaviate, pgvector, OpenSearch, Azure AI Search, or cloud-native equivalents.
- Familiarity with cloud AI services and model platforms across AWS, Azure, or GCP, and with enterprise authentication and security patterns.
- Experience deploying AI services using FastAPI, containers, serverless platforms, or Kubernetes, and integrating them into web or enterprise applications.
- Experience with fine-tuning, model adaptation, synthetic data generation, or advanced retrieval techniques is practical but not required.

What Success Looks Like

- You can take an ambiguous business problem and build an AI system that goes beyond a demo to complete meaningful tasks reliably.
- You can design and implement a multi-agent architecture with explicit orchestration, governed tools, state, evaluation, observability, and failure handling.
- You can diagnose why an agent fails on real tasks and improve the system using evidence from traces, evals, user feedback, and production behaviour.
- You make pragmatic choices between a simple deterministic workflow, a single agent, and a multi-agent system rather than adding agents where they are unnecessary.
- You create reusable technical patterns that help multiple product teams build safer and more reliable AI applications.

What We Offer

- Opportunity to build AI, data, analytics, and digital products across Retail & CPG, Media & Entertainment, Sports, Energy, Telecommunications, and other industries.
- Hands-on work with frontier and enterprise foundation models, modern agent frameworks, and emerging AI development patterns.
- Opportunity to take AI solutions from prototypes through evaluation, enterprise integration, production deployment, and continuous improvement.
- Exposure to Databricks, Snowflake, AWS, Azure, GCP, and modern cloud-native AI technologies without being constrained to a single platform.
- A development path toward Senior Applied AI Engineer, AI Architect, Agentic AI Lead, or technical leadership roles.

About EXL

EXL (NASDAQ:EXLS) is a global data and AI company that helps clients improve business outcomes through data, analytics, AI, digital solutions, and operations. Our teams work with organisations across industries to design, build, and deploy technology-driven solutions addressing complex business problems. Headquartered in New York, EXL has more than 40,000 professionals in locations throughout the United States, Europe, Asia (primarily India and Philippines), Latin America, Australia and South Africa.

📌 Applied AI Engineer - Agentic Systems (Gurugram)
🏢 EXL
📍 Gurugram