We are seeking a Senior AI Engineer LLM & Agent Design to architect, build, and scale production-grade intelligent agents for enterprise and BFSI use cases. This role focuses on LLM-powered agentic systems, memory management, Retrieval Augmented Generation (RAG), and robust AI workflows deployed in real-world environments.

You will work at the intersection of advanced AI research and enterprise engineering, collaborating with Product, Data, and Platform teams to deliver secure, scalable, and responsible AI solutions. Your work will directly influence how intelligent automation, copilots, and enterprise assistants are designed and deployed at scale.

Key Responsibilities :

LLM Agent Architecture & Design :

Architect and develop LLM-powered agents with advanced :

- Tool and function calling

- Planning and decision-making

- Multi-turn reasoning and state management

- Design agentic systems with orchestration logic and autonomous execution.

- Build multi-agent systems, planners, and collaborative agent frameworks.

Memory Systems & Context Management :

- Design and implement short-term and long-term memory architectures.

- Build vector stores, episodic memory, and semantic memory pipelines.

- Optimize context windows, memory schemas, and retrieval relevance.

- Implement memory graphs and knowledge retention strategies for agents.

Retrieval Augmented Generation (RAG) :

- Design and operationalize RAG pipelines for enterprise knowledge access.

Implement :

- Document chunking and indexing strategies

- Retrieval pipelines and context injection

- Embedding generation and similarity search

- Optimize RAG performance for latency, accuracy, and cost.

- Build evaluation frameworks for grounding, factuality, and relevance (BLEU/ROUGE, custom metrics).

End-to-End AI Engineering & MLOps :

Own the AI engineering lifecycle :

- Data pipelines

- Model integration

- Evaluation and validation

- Deployment and monitoring

- Build CI/CD pipelines for LLM applications and agent workflows.

- Manage model versioning, experiment tracking, and rollback strategies.

- Implement observability using logging, metrics, and tracing (Prometheus/OpenTelemetry).

Production Readiness & Responsible AI :

- Optimize cost, latency, throughput, and reliability of LLM systems.

- Implement guardrails, safety mechanisms, and hallucination mitigation.

- Ensure data privacy, PII handling, and regulatory compliance, especially for BFSI use cases.

- Drive adoption of responsible and ethical AI practices.

Collaboration & Leadership :

- Work closely with Product, Data, Platform, and Security teams.

- Mentor junior engineers and provide technical leadership.

- Define best practices, coding standards, and design guidelines for LLM and agent engineering.

- Contribute to architectural decisions and long-term AI strategy.

You Might Be Our Ideal Match If You :

Experience & Core Skills :

- Have 7 to 8 years of experience in software and AI engineering.

- Possess 3+ years of hands-on experience with LLMs and agent frameworks.

- Are highly proficient in Python (mandatory).

- Have working experience in TypeScript, Java, or Go (good to have).

LLM & Agent Frameworks :

Experience with LangChain, LlamaIndex, DSPy, OpenAI Assistants, Semantic Kernel, AgentQL.

Strong understanding of :

- Tool calling and function calling

- Agent orchestration and planning

- Prompt design, chaining, and optimization

Vector Databases & RAG :

- Expertise in FAISS, Pinecone, Weaviate, Milvus.

- Strong understanding of :

a. Embedding models

b. Similarity search and indexing strategies

c. Vector optimization and retrieval tuning

- Deep knowledge of RAG architectures and evaluation.

Cloud, MLOps & Observability :

- Hands-on experience with AWS, Azure, or GCP.

- Experience building CI/CD pipelines for ML/LLM systems.

- Knowledge of :

a. Model versioning and experiment tracking

b. Observability tools (Prometheus, logging, tracing)

- Familiarity with microservices and distributed systems.

Advanced & Good-to-Have Skills :

- Fine-tuning techniques (LoRA, PEFT, distillation, quantization).

- Multi-agent collaboration and coordination strategies.

- Memory graphs and knowledge graphs.

- Event-driven architectures and streaming systems.

- Message queues (Kafka, Redis).

- Experience deploying AI copilots or enterprise assistants in production.

- Proven experience running LLM applications at scale.

Education : BE / BTech / MTech / MS in Computer Science, AI/ML, Data Science, or related fields

(or equivalent practical experience)

The job is for:

Women candidates preferred

Differently-abled candidates preferred

Ex-defence personnel preferred

For women joining back the workforce