Back to all open roles
Engineering & AI
AI & LLM Systems Engineer
Bengaluru / Remote (India) • Full-time / Contract • 2 - 5 yrs • Competitive INR + Cloud GPU Credits
OVERVIEW
About the role
Architect autonomous multi-agent systems, domain-specific RAG pipelines, and production LLM integrations for forward-looking ventures.
RESPONSIBILITIES
What you'll do
- Implement production-grade RAG systems combining vector embeddings, hybrid search, and semantic re-ranking.
- Design reliable agentic workflows using Python, LangChain/LlamaIndex, OpenAI, Claude, and Gemini APIs.
- Build automated evaluation harnesses and prompt guardrails to prevent hallucinations and model drift.
- Integrate AI pipelines into production frontends with streaming token responses and low latency.
REQUIREMENTS
What we're looking for
Python OpenAI / Gemini / Claude APIs RAG / Vector Databases (pgvector) LangChain / Agents FastAPI
CULTURE & PERKS
Why Startupbricks
- Unlimited compute credits on leading LLM providers
- Direct collaboration with AI startup founders
- Fast prototyping cycles
Apply for this position
Direct review by hiring team. Guaranteed response in 48 hours.
Application Submitted!
Thank you for applying to Startupbricks. Our team will review your profile and reach out within 48 hours.
← Explore more open roles