Bangalore | Full time A rapid-growing AI-native LegalTech startup is hiring an AI Engineer to build and ship production-grade AI features and the infrastructure needed to evaluate and scale them reliably.
What you’ll work on:
Build LLM evaluation/model harnesses , regression suites and benchmarking infrastructure.
Develop production LLM-powered features from prototype to scale.
Build RAG pipelines, agentic workflows, tool-use systems and orchestration layers .
Design prompts, context strategies and AI system architectures.
Integrate and evaluate proprietary & open-source foundation models .
Own AI production reliability — monitoring, guardrails, fallbacks and observability .
Work closely with product, engineering and domain experts to solve complex workflow problems.
What we’re looking for:
3+ years building production AI/LLM applications.
Strong experience with LLMs, RAG and agentic/tool-use systems .
Experience building AI evals, test suites, benchmarks or model harnesses .
Strong Python/backend software engineering fundamentals.
Hands-on experience with prompt engineering and LLM orchestration .
Understanding of API-based and open-source models and model selection trade-offs.
Robust ownership, speed and ability to work independently.
Ideal profile: An AI engineer who can go beyond prompting — build the harness, ship the AI feature, evaluate it rigorously, and own it in production.