AI Engineer
About the role
We're looking for a hands-on AI Engineer to build LLM-powered applications and agents from natural-language interfaces over data to multi-step agentic workflows. You'll take ideas from prototype to reliable production: designing prompts and tools, wiring up retrieval, and most importantly making LLM systems that are trustworthy, not just impressive in a demo. This is a builder's role for someone who has actually shipped LLM agents, not only experimented with them.
What you'll do
Build and ship LLM-powered features and agents: retrieval, tool/function calling, and multi-step orchestration.
Turn prototypes into production-grade services: robust prompts, structured outputs, error handling, and sensible fallbacks.
Design and grow evaluation harnesses: measure output quality and catch regressions, so we ship on evidence, not vibes.
Add the guardrails that keep LLM systems honest: validation, safe defaults, and knowing when to ask or decline rather than guess.
Work across current and upcoming projects, and collaborate closely with domain experts and researchers.
Instrument what you build (logging, tracing) so behavior is observable and failures are debuggable.
What we're looking for
Minimum 1–2 years of experience in building LLM-powered applications, with at least one production-grade agent or multi-step LLM pipeline delivered end-to-end beyond notebooks or proof-of-concept demonstrations.
Strong programming proficiency in Python.
Hands-on experience with modern LLM application development, including prompt engineering, structured/JSON outputs, tool and function calling, Retrieval-Augmented Generation (RAG), and multi-step orchestration frameworks.
Proficiency in SQL and experience working with large, real-world, and heterogeneous datasets.
Strong analytical and evaluation skills, with the ability to identify failure modes, assess model performance, and measure application quality using systematic evaluation approaches rather than relying solely on demonstration results.
Strong focus on correctness, robustness, and reliability, with experience designing AI systems that provide accurate responses, handle uncertainty appropriately, and gracefully decline to answer when confidence is low or the request is outside the system's capabilities.
Able to work onsite in Bangalore.
Nice to have
RAG at depth / vector search & embeddings (pgvector, sentence-transformers, etc.).
Text-to-SQL or natural-language-to-query systems.
FastAPI / building APIs, tool servers, or MCP.
Observability and evaluation for LLM systems in production.
Interest in AI for public good / social-impact domains.
ARTPARK @ IISc : Innovation factory for next-gen robotics & AI
ARTPARK is India's leading deep-tech venture builder and incubator focused on robotics, connected autonomous systems, and AI. Leveraging our unique facilities and ecosystems, we strive to provide meaningful support to very early-stage startups building deep-tech products based in research. We are a nonprofit organization created by Indian Institute of Science (IISc, Bengaluru) with support from the Department of Science & Technology (Government of India) and the Government of Karnataka.