Hiring: Generative AI Engineer – Agentic AI & LLM Systems

We are looking for a skilled Generative AI Engineer with hands-on experience building LLM-powered applications, autonomous AI agents, multi-agent systems, and production-ready Retrieval-Augmented Generation (RAG) pipelines.

The ideal candidate should have strong Python skills and practical experience with LangChain, LangGraph, LLM integration, prompt engineering, and deploying scalable Generative AI solutions.

Key Responsibilities

- Design, develop, and deploy autonomous AI agents and multi-agent systems using LangGraph and LangChain.
- Build production-ready RAG pipelines using embeddings, semantic chunking, vector databases, and retrieval optimization.
- Integrate LLMs from providers such as OpenAI, Anthropic Claude, Google Gemini, Groq, and open-source model ecosystems.
- Implement prompt engineering, structured outputs, function calling, tool integration, and context management.
- Develop agentic workflows using supervisor orchestration, reflection loops, critic agents, and human-in-the-loop mechanisms.
- Build LLM evaluation frameworks using golden datasets, LLM-as-a-judge, regression testing, and output validation.
- Implement guardrails and hallucination mitigation strategies to improve the reliability of AI-generated responses.
- Develop backend services and REST APIs for LLM applications using Python, FastAPI, Flask, or Django.
- Implement LLMOps practices, including tracing, observability, prompt versioning, and token and cost monitoring.
- Optimize LLM application performance, retrieval quality, latency, and inference costs.
- Deploy and maintain Generative AI applications using cloud infrastructure, Docker, and CI/CD pipelines.
- Collaborate with cross-functional teams to translate business requirements into scalable AI-powered solutions.

Required Skills

Programming: Python, SQL
Generative AI & LLMs: OpenAI, Claude, Gemini, Groq,



Hugging Face, Ollama
Agentic AI: LangChain, LangGraph, multi-agent orchestration, supervisor workflows, tool calling, reflection and critic loops
RAG: Embeddings, semantic chunking, vector search, multi-query retrieval, contextual retrieval, source-grounded generation
Prompt Engineering: Few-shot prompting, structured prompting, function calling, Pydantic, JSON outputs
LLMOps & Evaluation: LangSmith, LLM evaluation, LLM-as-a-judge, guardrails, tracing, observability, regression testing, prompt management, token and cost monitoring
Backend Development: FastAPI, Flask, Django, REST APIs, microservices
Databases & Vector Stores: PostgreSQL, ChromaDB, Qdrant
Cloud & DevOps: AWS, Azure, Docker, Linux, Git, GitHub, CI/CD

Preferred Qualifications

- Hands-on experience building and deploying production-grade Generative AI applications.
- Strong understanding of RAG architectures, vector search, embeddings, and retrieval optimization.
- Experience designing autonomous agent workflows and integrating external tools and APIs.
- Knowledge of LLM evaluation, hallucination mitigation, responsible AI practices, and observability.
- Experience deploying scalable AI services using cloud platforms and containerization.
- Robust problem-solving, communication, and collaboration skills.

Job Details

Role: Generative AI Engineer – Agentic AI & LLM Systems
Experience: 2+ years
Employment Type: Full-time
Location: Jayanagar 7th Block
Work Mode: On-site

Interested candidates can share their updated resumes at [email protected]

Pay: ₹40,000.00 - ₹50,000.00 per month

Benefits:

- Health insurance

Application Question(s):

- Do you have at least 2 years of hands-on experience in Generative AI or LLM application development?
- Have you integrated LLM APIs such as OpenAI, Google Gemini, or Claude?
- Have you deployed applications using Docker and cloud platforms?

Work Location: In person

📌 Generative AI Engineer (Jayanagar)
🏢 Brewkspace
📍 Jayanagar