Artificial Intelligence Engineer

Company Description Neural Foundry is dedicated to building truly intelligent robots that go beyond traditional assembly-line automation. The company focuses on adaptive Artificial Intelligence combined with thoughtfully engineered hardware to address real-world needs. By integrating advanced AI techniques into practical, user-friendly robotic systems, Neural Foundry aims to make intelligence tangible and accessible. Team members work at the intersection of software and hardware, contributing to products that bring cutting-edge research into everyday applications. This environment offers the opportunity to solve complex challenges and help define the future of intelligent robotics.

Role Description As an Artificial Intelligence Engineer at Neural Foundry, you will design, implement, and optimize AI models that power intelligent robotic systems, automation workflows. Day-to-day responsibilities include developing algorithms for pattern recognition, building and training neural networks, and integrating AI components into production-grade software. You will collaborate closely with robotics, hardware, and software teams to test, refine, and deploy AI solutions on physical devices, as well as analyze performance data to improve accuracy and robustness. The role also involves exploring applications of natural language processing and other AI techniques to enhance human–robot interaction. This is a full-time, on-site position based in Hyderabad.

• 3–5 years in software engineering, with at least 1–2 years focused on LLM-based systems in production (not just prototypes).
• Demonstrated prompt-engineering depth: structured extraction from long, complex documents — not just chat/Q&A use cases. Experience with few-shot, chain-of-thought, and schema-constrained outputs.
• Hands-on experience with an agent/orchestration framework (LangGraph strongly preferred; LangChain, CrewAI, or Autogen acceptable).
• Solid Python — you can build FastAPI endpoints, write async code, and work with MongoDB/Redis without hand-holding.
• Familiarity with evaluation methodology for LLM outputs: building test sets, measuring precision/recall at the field level, tracking regressions.

• Experience in a regulated industry (pharma, life sciences, finance, healthcare) where data accuracy and audit trails are non-negotiable.
• Prior work on document-to-structured-data pipelines (not just summarisation or RAG).
• Experience with LLM observability tools (Langfuse, LangSmith, Braintrust, or similar).
• Understanding of XML schema design or hierarchical data models.
• Exposure to OpenAI function-calling / structured outputs and cost-optimisation strategies (prompt caching, model routing).