AI Engineer - LLM & Agent Design

Description :

Location : Bangalore

Experience : 3 - 6 Years

Notice Period : Immediate to 15 Days

Role Overview :

We are seeking a Senior AI Engineer LLM Agent to join our dynamic team in the ITES sector. This role is pivotal in designing, building, and deploying LLM-driven intelligent agents with strong focus on memory management, retrieval, context handling, and real-world production workflows.

You will work on cutting-edge agentic AI systems, enabling scalable, reliable, and safe AI-powered applications. This is an excellent opportunity to shape next-generation AI solutions that enhance user experience, automation, and operational efficiency for enterprise clients.

Key Roles & Responsibilities :

LLM Agent & AI System Development :

- Design and build LLM-based agents with tool/function calling and conversation state management.

- Implement multi-turn dialogue handling and optimize context window utilization.

- Develop agent workflows with planning, reasoning, and decision-making capabilities.

- Build short-term and long-term memory schemas for conversational and task-based agents.

- Optimize memory retrieval strategies to ensure context relevance and accuracy.

Retrieval-Augmented Generation (RAG) :

- Design and implement RAG pipelines with efficient document chunking strategies.

- Integrate vector stores and build scalable retrieval pipelines.

- Implement retrieval strategies and intelligent context injection mechanisms.

- Work with embeddings, similarity search, and relevance optimization.

Backend & Platform Engineering :

- Develop robust, scalable Python services for AI workloads.

- Build and expose REST / GraphQL APIs for LLM-based services.

- Design systems using microservices architecture.

- Integrate AI services with cloud platforms and data infrastructure.

- Implement logging, monitoring, error handling, and system observability.

Safety, Evaluation & Reliability :

- Implement guardrails and safety mechanisms for LLM outputs.

- Instrument systems for evaluation, monitoring, and performance tracking.

- Build prompt templates, orchestration logic, and fallback strategies.

- Ensure production readiness, scalability, and fault tolerance.

You Might Be Our Ideal Match If You :

Core Experience :

- Have 3- 5 years of experience in software engineering or ML engineering.

- Bring 1- 2 years of hands-on experience building LLM-based systems or agents.

- Are proficient in Python (mandatory).

LLM & Agent Expertise :

- Have experience with LLM agent frameworks such as LangChain, LlamaIndex, or DSPy.

- Are skilled in prompt engineering, prompt templates, and orchestration logic.

- Have hands-on experience with RAG implementations and guardrails.

- Understand memory management, context windows, and conversation state.

Vector Databases & Retrieval :

- Have experience with vector stores such as FAISS, Pinecone, or Weaviate.

- Understand embeddings, similarity search, and vector indexing fundamentals.

APIs, Cloud & DevOps :

- Have experience building and integrating REST / GraphQL APIs.

- Are familiar with microservices and cloud deployment on AWS, Azure, or GCP.

- Use Git and follow version control best practices.

Good to Have :

- Experience integrating with OpenAI, Azure OpenAI, Claude, or Meta LLMs.

- Hands-on experience with local model deployment (Llama, Mistral).

- Understanding of MLOps basics including Docker, CI/CD pipelines.

- Familiarity with model/version management and observability (logs, metrics, traces).

Education :

- BE / BTech in Computer Science, Information Technology, or equivalent practical experience.